MACHINE LEARNING
PROJECTS
PEOPLE
PATENTS
We study the problem of length generalization (LG) in transformers: the ability of a model trained on shorter sequences to maintain performance when evaluated on much longer, previously unseen inputs. Prior work by Huang et al. (2025) established that transformers eventually achieve length generalization
Radiology report generation requires advanced medical image analysis, effective temporal reasoning, and accurate text generation. Although recent innovations, particularly multimodal large language models (MLLMs), have shown improved performance, their supervised fine-tuning (SFT) objective is not explicitly
Large Language Models (LLMs) have demonstrated remarkable capabilities in understanding and generating human-like text, yet they largely operate as reactive agents, responding only when directly prompted. This passivity creates an “awareness gap,” limiting their potential as truly collaborative partners
Cell fate decisions are highly coordinated processes governed bycomplex interactions among numerous regulatory genes, whiledisruptions in these mechanisms can lead to developmental abnormalitiesand disease. Traditional methods often fail to capture suchcombinatorial interactions, limiting their ability
Question Answering (QA) accounts for a significantportion of LLM usage “in the wild”.However, LLMs sometimes produce false ormisleading responses, also known as hallucinations.Therefore, grounding the generatedanswers in contextually provided information—i.e., providing evidence for the generated
Adapting large Video-Language Models (VLMs) for action detection using only a few examples poses challenges like overfitting and the granularity mismatch between scene-level pre-training and required person-centric understanding. We propose an efficient adaptation strategy combining parameter-efficient
We provide quantitative bounds on the length of sequences required to be observed during training for a transformer to length generalize, e.g., to continue to perform well on sequences unseen during training. Our results improve on Huang et al. [8], who show that there is a finite training length beyond
Designing protein-binding proteins with high affinity is critical in biomedical research and biotechnology. Despite recent advancements targeting specific proteins, the ability to create high-affinity binders for arbitrary protein targets on demand, without extensive rounds of wet-lab testing,remains
Tumor-infiltrating lymphocytes (TILs) are a provocative biomarker in melanoma, influencing diagnosis, prognosis, and immunotherapy outcomes; however, traditional pathologistreadTIL assessment on hematoxylin and eosin–stained slides is prone to interobserver variability, leading to inconsistent clinical
Diffusion models (DMs) have proven to be effective in modeling high-dimensional distributions, leading to their widespread adoption for representing complex priors in Bayesian inverse problems (BIPs). However, current DM-based posterior sampling methods proposed for solving common BIPs rely on heuristic
A major challenge in near-term quantum computing is its application to large real-world datasets due to scarce quantum hardware resources. One approach to enabling tractable quantum models for such datasets involves finding low-dimensional representations that preserve essential information for downstream
Despite the recent impressive breakthroughs in text-to-image generation, generative models have difficulty in capturing thedata distribution of underrepresented attribute compositions while over-memorizing overrepresented attribute compositions,which raises public concerns about their robustness and
We consider the conditional generation of 3D drug-like molecules with explicit control over molecular properties such as drug-like properties (e.g., Quantitative Estimate of Druglikenessor Synthetic Accessibility score) and effectively binding to specific protein sites. To tackle this problem, we propose
Action detection aims to detect (recognize and localize) human actions spatially and temporally in videos. Existing approaches focus on the closed-set setting where an action detector is trained and tested on videos from a fixed set of action categories. However, this constrained setting is not viable
Unarguably deep learning models capable of generalizing to unseen domain data while leveraging a few labels are of great practical significance due to low developmental costs. In search of this endeavor we study the challenging problem of semi-supervised domain generalization (SSDG) where the goal is
Multimodal Large Language Models (MLLMs) have shown impressive performance in vision and text tasks. However, hallucination remains a major challenge, especially in fields like healthcare where details are critical. In this work, we show how MLLMs may be enhanced to support Visual RAG (V-RAG), a retrieval-augmented
Non-small cell lung cancer (NSCLC) shows variable responses to immunotherapy, highlighting the need for biomarkers to guide patient selection. We applied a spatial multi-omics approach to 234 advanced NSCLC patients treated with programmed death 1-based immunotherapy across three cohorts to identify
Variational optimization (VO) offers a general approach for handling objectives which may involve discontinuities, or whose gradients are difficult to calculate. By introducing a variational distribution over the parameter space, such objectives are smoothed, and rendered amenable to VO methods. Local
We study the problem of subgroup discovery with Cox regression models and introduce a method for finding an interpretable subset of the data on which a Cox model is highly accurate. Our method relies on two technical innovations: the emph (Unknown sysvar: (expected prediction entropy)), a novel metric
Transcriptional regulation through cis-regulatory elements (CREs) is crucial for numerous biological functions, with its disruption potentially leading to various diseases. It is well-known that these CREs often exhibit redundancy, allowing them to compensate for each other in response to external
Action detection aims to detect (recognize and localize) human actions spatially and temporally in videos. Existing approaches focus on the closed-set setting where an action detector is trained and tested on videos from a fixed set of action categories. However, this constrained setting is not viable
The problem of calibrating deep neural networks (DNNs) is gaining attention, as these networks are becoming central to many real-world applications. Different attempts have been made to counter the poor calibration of DNNs. Amongst others, train-time calibration methods have unfolded as an effective
Graph neural networks (GNNs) have emerged as powerful tools for representation learning. Their efficacy depends on their having an optimal underlying graph. In many cases, the most relevant information comes from specific subgraphs. In this work, we introduce a GNN-based framework (graph-partitioned
Separating disinformation from fact on the web has long challenged both the search and the reasoning powers of humans. We show that the reasoning power of large language models (LLMs) and the retrieval power of modern search engines can be combined to automate this process and explainably verify claims.
Levels of selection and multilevel evolutionary processes are essential concepts in evolutionary theory, and yet there is a lack of common mathematical models for these core ideas. Here, we propose a unified mathematical framework for formulating and optimizing multilevel evolutionary processes and genetic
When performing complex multi-step reasoning tasks, the ability of Large Language Models (LLMs) to derive structured intermediate proof steps is important for ensuring that the models truly perform the desired reasoning and for improving models’ explainability. This paper is centered around a focused
Learning to localize temporal boundaries of procedure steps in instructional videos is challenging due to the limited availability of annotated large-scale training videos. Recent works focus on learning the cross-modal alignment between video segments and ASR-transcripted narration texts through contrastive
Spatial transcriptomics technologies, which generate a spatial map of gene activity, can deepen the understanding of tissue architecture and its molecular underpinnings in health and disease. However, the high cost makes these technologies difficult to use in practice. Histological images co-registered
Multi-camera tracking plays a pivotal role in various real-world applications. While end-to-end methods have gained significant interest in single-camera tracking, multi-camera tracking remains predominantly reliant on heuristic techniques. In response to this gap, this paper introduces Multi-Camera
We aim to improve the prediction of response or resistance to immunotherapies in patients with melanoma. This goal is based on the hypothesis that current gene signatures predicting immunotherapy outcomes show only modest accuracy due to the lack of spatial information about cellular functions and molecular
A major challenge in near-term quantum computing is its application to large real-world datasets due to scarce quantum hardware resources. One approach to enabling tractable quantum models for such datasets involves compressing the original data to manageable dimensions while still representing essential
We present an approach for estimating the fraction of text in a large corpus which is likely to be substantially modified or produced by a large language model (LLM). Our maximum likelihood model leverages expert-written and AI-generated reference texts to accurately and efficiently examine real-world
In this paper, we introduce efforts to apply large language models (LLMs) to the field of material development. NEC is advancing the development of a material development platform. By applying core technologies corresponding to two material development steps, namely investigation activities (Read paper/patent)
Weakly Supervised Temporal Action Localization (WSTAL) aims to jointly localize and classify action segments in untrimmed videos with only video level annotations. To leverage video level annotations most existing methods adopt the multiple instance learning paradigm where frame/snippet level action
The study of complex human interactions and group activities has become a focal point in human-centric computer vision. However, progress in related tasks is often hindered by the challenges of obtaining large-scale labeled datasets from real-world scenarios. To address the limitation, we introduce M3Act,
In this paper we explore the capability of an agent to construct a logical sequence of action steps thereby assembling a strategic procedural plan. This plan is crucial for navigating from an initial visual observation to a target visual outcome as depicted in real-life instructional videos. Existing
Motivation Spatial transcriptomics technologies, which generate a spatial map of gene activity, can deepen the understanding of tissue architecture and its molecular underpinnings in health and disease. However, the high cost makes these technologies difficult to use in practice. Histological images
In the field of histopathology, computer-aided systems face significant challenges due to diverse domain shifts. They include variations in tissue source organ, preparation and scanningprotocols. These domain shifts can significantly impact algorithms performance in histopathology tasks, such as cancer
Recent advances in spatial transcriptomics allow spatially resolved gene expression measurements with cellular or even sub-cellular resolution, directly characterizing the complex spatiotemporal gene expression landscape and cell-to-cell interactions in their native microenvironments. Due to technology
The development of next-generation sequencing (NGS) has enabled the discovery of cancer-specific driver gene alternations, making precision medicine possible. However, accurategenetic testing requires a sufficient amount of tumor cells in the specimen. The evaluation of tumor content ratio (TCR) from
Camouflaged object detection (COD) is the challenging task of identifying camouflaged objects visually blended into surroundings. Albeit achieving remarkable success, existing COD detectors still struggle to obtain precise results in some challenging cases. To handle this problem, we draw inspiration
In applications involving sensitive data, such as finance and healthcare, the necessity for preserving data privacy can be a significant barrier to machine learning model development.Differential privacy (DP) has emerged as one canonical standard for provable privacy. However, DPs strong theoretical
Self-consistency has emerged as a powerful method for improving the accuracy of short answers generated by large language models. As previously defined, it only concerns the accuracy of a final answer parsed from generated text. In this work, we extend the idea to open response generation, by integrating
In protein biophysics, the separation between the functionally important residues (forming the active site or binding surface) and those that create the overall structure (the fold) is a well-established and fundamental concept. Identifying and modifying those functional sites is critical for protein
Weakly-Supervised Concealed Object Segmentation (WSCOS) aims to segment objects well blended with surrounding environments using sparsely-annotated data for model training. It remains a challenging task since (1) it is hard to distinguish concealed objects from the background due to the intrinsic similarity
This paper studies source-free domain adaptive fundus image segmentation which aims to adapt a pretrained fundus segmentation model to a target domain using unlabeled images. This is a challenging task because it is highly risky to adapt a model only using unlabeled data. Most existing methods tackle
Heterogeneous image fusion (HIF) aims to enhance image quality by merging complementary information of images captured by different sensors. Early model-based approaches have strong interpretability while being limited by non-adaptive feature extractors with poor generalizability.
Recent few-shot video classification (FSVC) works achieve promising performance by capturing similarity across support and query samples with different temporal alignment strategies or learning discriminative features via Transformer block within each episode. However, they ignore two important issues:
Few-Shot Segmentation FSS (Few-shot segmentation) aims to segment a target class using a small number of labeled images (support set). To extract information relevant to the target class, a dominant approach in best performing FSS methods removes background features using a support mask. We observe that
Federated learning casts a light on the collaboration of distributed local clients with privacy protected to attain a more generic global model. However, significant distribution shift in input/label space across different clients makes it challenging to well generalize to all clients, which motivates
When faced with a large number of product reviews, it is not clear that a human can remember all of them and weight opinions representatively to write a good reference summary. Wepropose an automatic metric to test the prevalence of the opinions that a summary expresses, based on counting the number
Cross-Domain Detection (XDD) aims to train a domain-adaptive object detector using unlabeled images from a target domain and labeled images from a source domain. Existing approaches achieve this either by aligning the feature maps or the region proposals from the two domains, or by transferring the style
Camouflaged object detection (COD) aims to address the tough issue of identifying camouflaged objects visually blended into the surrounding backgrounds. COD is a challenging task due to the intrinsic similarity of camouflaged objects with the background, as well as their ambiguous boundaries. Existing
Conditional image-to-video (cI2V) generation aims to synthesize a new plausible video starting from an image (e.g., a person’s face) and a condition (e.g., an action class label like smile). The key challenge of the cI2V task lies in the simultaneous generation of realistic spatial appearance and temporal
Diffusion probabilistic models have achieved enormous success in the field of image generation and manipulation. In this paper, we explore a novel paradigm of using the diffusion model and classifier guidance in the latent semantic space for compositional visual tasks. Specifically, we train latent diffusion
Source-free domain adaptation (SFDA) is an emerging research topic that studies how to adapt a pretrained source model using unlabeled target data. It is derived from unsupervised domain adaptation but has the advantage of not requiring labeled source data to learn adaptive models. This makes it particularly
Semi-Supervised Domain Adaptation (SSDA) is a recently emerging research topic that extends from the widely-investigated Unsupervised Domain Adaptation (UDA) by further having a few target samples labeled, i.e., the model is trained with labeled source samples, unlabeled target samples as well as a few
T cells monitor the health status of cells by identifying foreign peptides displayed on their surface. T-cell receptors (TCRs), which are protein complexes found on the surface of T cells, are able to bind to these peptides. This process is known as TCR recognition and constitutes a key step for immune
Source-free object detection (SFOD) aims to transfer a detector pre-trained on a label-rich source domain to an unlabeled target domain without seeing source data. While most existing SFOD methods generate pseudo labels via a source-pretrained model to guide training, these pseudo labels usually contain
Motivation: MHC Class I protein plays an important role in immunotherapy by presenting immunogenic peptides to anti-tumor immune cells. The repertoires of peptides for various MHC Class I proteins are distinct, which can be reflected by their diverse binding motifs. To characterize binding motifs for
This paper presents a framework for real-time concealed weapon detection (CWD) on 3D radar images for walk-through screening systems. The walk-through screening system aims to ensure security in crowded areas by performing CWD on walking persons, hence it requires an accurate and real-time detection
Several recent studies investigate TCR-peptide/-pMHC binding prediction using machine learning or deep learning approaches. Many of these methods achieve impressive results on test sets, which include peptide sequences that are also included in the training set. In this work, we investigate how state
We present a multi-sequence generalization of Variational Information Bottleneck and call the resulting model Attentive Variational Information Bottleneck (AVIB). Our AVIB model leverages multi-head self-attention to implicitly approximate a posterior distribution over latent encodings conditioned on
Knowledge Graphs (KGs) store information in the form of (head, predicate, tail)-triples. To augment KGs with new knowledge, researchers proposed models for KG Completion (KGC) tasks such as link prediction, i.e., answering (h, p, ?) or (?, p, t) queries. Such models are usually evaluated with averaged
Group Activity Recognition detects the activity collectively performed by a group of actors, which requires compositional reasoning of actors and objects. We approach the task by modeling the video as tokens that represent the multi-scale semantic concepts in the video. We propose COMPOSER, a Multiscale
Anomaly Detection (AD) aims to find defective patterns or abnormal samples among data, and has been a hot research topic due to various real-world applications. While various AD methods have been proposed, most of them assume the availability of a clean (anomaly-free) training set, which, however, may
Product reviews may have complex discourse including coreference and bridging relations to a main product, competing products, and interacting products. Current approaches to aspect-based sentiment analysis (ABSA) and opinion summarization largely ignore this complexity. On the other hand, existing systems
Predicting the interactions between T-cell receptors (TCRs) and peptides is crucial for the development of personalized medicine and targeted vaccine in immunotherapy. Current datasets for training deep learning models of this purpose remain constrained without diverse TCRs and peptides. To combat the
Although progress has been made for text-to-image synthesis, previous methods fall short of generalizing to unseen or underrepresented attribute compositions in the input text. Lacking compositionality could have severe implications for robustness and fairness, e.g., inability to synthesize the face
Self-supervised video representation learning has been shown to effectively improve downstream tasks such as video retrieval and action recognition. In this paper, we present the Cascade Positive Retrieval (CPR) that successively mines positive examples w.r.t. the query for contrastive learning in a
We study few-shot debugging of transformer based natural language understanding models, using recently popularized test suites to not just diagnose but correct a problem. Given a few debugging examples of a certain phenomenon, and a held-out test set of the same phenomenon, we aim to maximize accuracy
StyleGANs have shown impressive results on data generation and manipulation in recent years, thanks to its disentangled style latent space. A lot of efforts have been made in inverting a pretrained generator, where an encoder is trained ad hoc after the generator is trained in a two-stage fashion. In
The recent success of deep learning applications has coincided with those widely available powerful computational resources for training sophisticated machine learning models with huge datasets. Nonetheless, training large models such as convolutional neural networks using model parallelism (as opposed
Molecule optimization is a critical step in drug development to improve the desired properties of drug candidates through chemical modification. We have developed a novel deep generative model, Modof, over molecular graphs for molecule optimization. Modof modifies a given molecule through the prediction
Image captioning systems are expected to have the ability to combine individual concepts when describing scenes with concept combinations that are not observed during training. In spite of significant progress in image captioning with the help of the autoregressive generation framework, current approaches
We develop a system for the FEVEROUS fact extraction and verification task that ranks an initial set of potential evidence and then pursues missing evidence in subsequent hops by trying to generate it, with a “next hop prediction module” whose output is matched against page elements in a predicted
Non-muscle invasive bladder cancer (NMIBC) generally has a good prognosis, however, recurrence after transurethral resection (TUR), the standard primary treatment, is a major problem. Clinical management after TUR has been based on risk classification using clinicopathological factors, but these classifications
Conditional Generative Adversarial Networks (cGANs) extend the standard unconditional GAN framework to learning joint data-label distributions from samples, and have been established as powerful generative models capable of generating high-fidelity imagery. A challenge of training such a model lies in
Action recognition is an important problem that requires identifying actions in video by learning complex interactions across scene actors and objects. However, modern deep-learning based networks often require significant computation and may capture scene context using various modalities that further
Recent studies have demonstrated the vulnerability of deep neural networks against adversarial examples. In-spired by the observation that adversarial examples often lie outside the natural image data manifold and the intrinsic dimension of image data is much smaller than its pixel space dimension, we
Modern natural language understanding models depend on pretrained subword embeddings, but applications may need to reason about words that were never or rarely seen during pretraining. We show that examples that depend critically on a rarer word are more challenging for natural language inference models.
MotivationMapping distal regulatory elements, such as enhancers, is a cornerstone for elucidating how genetic variations may influence diseases. Previous enhancer-prediction methods have used either unsupervised approaches or supervised methods with limited training data. Moreover, past approaches have
Learning disentangled representations leads to interpretable models and facilitates data generation with style transfer, which has been extensively studied on static data such as images in an unsupervised learning framework. However, only a few works have explored unsupervised disentangled sequential
This paper considers the problem of spatiotemporal object-centric reasoning in videos. Central to our approach is the notion of object permanence, i.e., the ability to reason about the location of objects as they move through the video while being occluded, contained or carried by other objects. Existing
T-cell receptors can recognize foreign peptides bound to major histocompatibility complex (MHC) class-I proteins, and thus trigger the adaptive immune response. Therefore, identifying peptides that can bind to MHC class-I molecules plays a vital role in the design of peptide vaccines. Many computational
We propose a method to accurately obtain the ratio of tumor cells over an entire histological slide. We use deep fully convolutional neural network models trained to detect and classify cells on images of H&E-stained tissue sections. Pathologists’ labels consisting of exhaustive nuclei locations and
One major source of vulnerability of neural nets in classification tasks is from overparameterized fully connected layers near the end of the network. In this paper, we propose a new neighborhood preserving layer which can replace these fully connected layers to improve the network robustness. Networks
Hepatocellular carcinoma (HCC) is a representative primary liver cancer caused by long-term and repetitive liver injury. Surgical resection is generally selected as the radical cure treatment. Because the early recurrence of HCC after resection is associated with low overall survival, the prediction
Deep neural networks have been widely applied for missing data imputation. However, most existing studies have been focused on imputing continuous data, while discrete data imputation is under-explored. Discrete data is common in real world, especially in research areas of bioinformatics, genetics, and
Localizing moments in untrimmed videos via language queries is a new and interesting task that requires the ability to accurately ground language into video. Previous works have approached this task by processing the entire video, often more than once, to localize relevant activities. In the real world
Learning disentangled representations of natural language is essential for many NLP tasks, e.g., conditional text generation, style transfer, personalized dialogue systems, etc. Similar problems have been studied extensively for other forms of data, such as images and videos. However, the discrete nature
We propose a sequential variational autoencoder to learn disentangled representations of sequential data (e.g., videos and audios) under self-supervision. Specifically, we exploit the benefits of some readily accessible supervision signals from input data itself or some off-the-shelf functional models
We propose a framework for answering open domain multi hop questions in which partial information is read and used to generate followup questions, to finally be answered by a pretrained single hop answer extractor. This framework makes each hop interpretable, and makes the retrieval associated with later
In this paper, we introduce a contextual grounding approach that captures the context in corresponding text entities and image regions to improve the grounding accuracy. Specifically, the proposed architecture accepts pre-trained text token embeddings and image object features from an off-the-shelf object
In this paper, we introduce a contextual grounding approach that captures the context in corresponding text entities and image regions to improve the grounding accuracy. Specifically, the proposed architecture accepts pre-trained text token embeddings and image object features from an off-the-shelf object
The rich and accessible labeled data fueled the revolutionary successes of deep learning in object recognition. However, recognizing objects of novel classes with limited supervision information provided, i.e., Novel Object Recognition (NOR), remains a challenging task. We identify in this paper two
Zero-shot learning (ZSL) aims to recognize instances of unseen classes solely based on the semantic descriptions of the classes. Existing algorithms usually formulate it as a semantic-visual correspondence problem, by learning mappings from one feature space to the other. Despite being reasonable, previous
Developing conditional generative models for text-to-video synthesis is an extremely challenging yet an important topic of research in machine learning. In this work, we address this problem by introducing Text-Filter conditioning Generative Adversarial Network (TFGAN), a conditional GAN model with a
Traditional embedding approaches associate a real-valued embedding vector with each symbol or data point, which is equivalent to applying a linear transformation to “one-hot” encoding of discrete symbols or data objects. Despite simplicity, these methods generate storage-inefficient representations
Localizing moments in untrimmed videos using language queries is a new task that requires the ability to accurately ground language into video. Existing approaches process the video, often more than once, to localize the activities and are inefficient. In this paper, we present TripNet, an end-to-end
In spite of its importance, passenger demand prediction is a highly challenging problem, because the demand is simultaneously influenced by the complex interactions among many spatial and temporal factors and other external factors such as weather. To address this problem, we propose a Spatio-TEmporal
Existing visual reasoning datasets, such as Visual Question Answering (VQA), often suffer from biases conditioned on the question, image or answer distributions. The recently proposed CLEVR dataset addresses these limitations and requires fine-grained reasoning, but the dataset is synthetic and consists
We introduce a new inference task – Visual Entailment (VE) – which differs from traditional Textual Entailment (TE) tasks whereby a premise is defined by an image, rather than a natural language sentence as in TE tasks. A novel dataset SNLI-VE is proposed for VE tasks based on the Stanford Natural Language
Recent studies have demonstrated the vulnerability of deep convolutional neural networks against adversarial examples. Inspired by the observation that the intrinsic dimension of image data is much smaller than its pixel space dimension and the vulnerability of neural networks grows with the input dimension,
Making predictions about what might happen in the future is important for reacting adequately in many situations. For example, observing that Man kidnaps girl may have the consequence that Man kills girl. While this is part of common sense reasoning for humans, it is not obvious how machines
Convolutional neural networks (CNNs) have recently emerged as a popular building block for natural language processing (NLP). Despite their success, most existing CNN models employed in NLP share the same learned (and static) set of filters for all input sentences. In this paper, we consider an approach
We develop a system for the FEVER fact extraction and verification challenge that uses a high precision entailment classifier based on transformer networks pretrained with language modeling, to classify a broad set of potential evidence. The precision of the entailment classifier allows us to enhance
Existing entailment datasets mainly pose problems which can be answered without attention to grammar or word order. Learning syntax requires comparing examples where different grammar and word order change the desired classification. We introduce several datasets based on synthetic transformations of
Parametric embedding methods such as parametric t-distributed Stochastic Neighbor Embedding (pt-SNE) enables out-of-sample data visualization without further computationally expensive optimization or approximation. However, pt-SNE favors small mini-batches to train a deep neural network but large mini-batches
In recent years, many techniques have been developed to improve the performance and efficiency of data center networks. While these techniques provide high accuracy, they are often designed using heuristics that leverage domain-specific properties of the workload or hardware.In this vision paper, we
Many deep learning architectures have been proposed to model the compositionality in text sequences, requiring substantial number of parameters and expensive computations. However, there has not been a rigorous evaluation regarding the added value of sophisticated compositional functions. In this paper,
Conventional embedding methods directly associate each symbol with a continuous embedding vector, which is equivalent to applying a linear transformation based on a one-hot encoding of the discrete symbols. Despite its simplicity, such approach yields the number of parameters that grows linearly
Human actions often involve complex interactions across several inter-related objects in the scene. However, existing approaches to fine-grained video understanding or visual relationship detection often rely on single object representation or pairwise object relationships. Furthermore, learning interactions
Previous models for video captioning often use the output from a specific layer of a Convolutional Neural Network (CNN) as video features. However, the variable context-dependent semantics in the video may make it more appropriate to adaptively select features from the multiple CNN layers. We propose
Generating videos from text has proven to be a significant challenge for existing generative models. We tackle this problem by training a conditional generative model to extract both static and dynamic information from text. This is manifested in a hybrid framework, employing a Variational Autoencoder
Adaptive Memory Networks We present Adaptive Memory Networks (AMN) that processes input-question pairs to dynamically construct a network architecture optimized for lower inference times for Question Answering (QA) tasks. AMN processes the input story to extract entities and stores them in memory banks.
