MACHINE LEARNING
PROJECTS
PEOPLE
PUBLICATIONS
PATENTS
We have developed a system for real-time scene understanding and reasoning across various domains such as safety, manufacturing, retail, healthcare, and personal assistance. This system continuously monitors and analyzes video, acoustics, and time series data related to human activities, aiming to provide a comprehensive understanding of ongoing situations. The project utilizes advanced AI models to process large volumes of data, generating actionable insights that help users grasp complex scenarios.
Through user interaction, the system builds detailed representations of these insights, which are then visualized to highlight significant patterns, trends, and anomalies. This visualization process enables users to make informed decisions quickly and accurately in dynamic and potentially high-stakes environments. Ultimately, the project aims to enhance situational awareness by integrating multiple data modalities, thereby improving response strategies and operational efficiency.
Team Members: Deep Patel, Iain Melvin, Martin Renqiang Min
Publication Tags: video understanding, action recognition, LLMs, large language models, large language model
Though Large Language Models (LLMs) have shown remarkable open-generation capabilities across diverse domains, they struggle with knowledge-intensive tasks. To alleviate this issue, knowledge integration methods have been proposed to enhance LLMs with domain-specific knowledge graphs using external modules.
Our new project, Time Series Language Model for Explainable AI, represents a significant leap forward in the field of forecasting and explainable AI. By combining advanced forecasting techniques with explainable AI, we are paving the way for a future where data-driven insights are not only accurate but
The development of Agentic LLMs for AI Orchestration represents a significant advancement in artificial intelligence. By seamlessly integrating computer vision, logic, and compute modules, our LLM is poised to revolutionize the way complex workflows are managed and executed. Supported by robust research
This paper introduces the retrieval-augmented large language model with Definite Finite Automaton (DFA-RAG), a novel framework designed to enhance the capabilities of conversational agents using large language models (LLMs). Traditional LLMs face challenges in generating regulated and compliant responses
Costs of LLM API usage rise rapidly when proprietary enterprise data is used as context for user queries to generate more accurate responses from LLMs. To reduce costs, we propose LeanContext, which generates query-aware, compact and AI model-friendly summaries of relevant enterprise data context. This
In-context learning has emerged as a groundbreaking ability of Large Language Models (LLMs) and revolutionized various fields by providing a few task-relevant demonstrations in the prompt. However, trustworthy issues with LLMs response, such as hallucination, have also been actively discussed. Existing
Large Language Models (LLMs) have exhibited remarkable proficiency across a wide array of NLP tasks. However, the escalation in model size also engenders substantial deployment costs. While few efforts have explored model pruning techniques to reduce the size of LLMs, they mainly center on general or
Autonomous vehicle (AV) systems rely on robust perception models as a cornerstone of safety assurance. However, objects encountered on the road exhibit a long-tailed distribution, with rare or unseen categories posing challenges to a deployed perception model. This necessitates an expensive process of
Retrieval-augmented generation (RAG) is used in natural language processing (NLP) to provide query-relevant information in enterprise documents to large language models (LLMs). Such enterprise context enables the LLMs to generate more informed and accurate responses. When enterprise data is primarily
Visual program synthesis is a promising approach to exploit the reasoning abilities of large language models for compositional computer vision tasks. Previous work has used few-shot prompting with frozen LLMs to synthesize visual programs. Training an LLM to write better visual programs is an attractive
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,
Extracting real-time insights from multi-modal data streams from various domains such as healthcare, intelligent transportation, and satellite remote sensing remains a challenge. High computational demands and limited knowledge scope restrict the applicability of Multi-Modal Large Language Models (MM-LLMs)
AI/ML techniques have been used to solve systems problems, but their applicability to customize solutions on-the-fly has been limited. Traditionally, any customization required manually changing the AI/ML model or modifying the code, configuration parameters, application settings, etc. This incurs too
Question-answering (QA) is a significant application of Large Language Models (LLMs), shaping chatbot capabilities across healthcare, education, and customer service. However, widespread LLM integration presents a challenge for small businesses due to the high expenses of LLM API usage. Costs rise rapidly
Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text, typically in the form of (subject, relation, object) triples. Despite the potential of large language models (LLMs) like ChatGPT as a general task solver, they lag behind state-of-the-art (supervised) methods
Retrieval augmented generation (RAG) systems combine the strengths of language generation and information retrieval to power many real-world applications like chatbots. Use of RAG for combined understanding of multimodal data such as text, images and videos is appealing but two critical limitations exist:
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
The recent progress in language-based object detection with an open-vocabulary can be largely attributed to finding better ways of leveraging large-scale data with free-form text annotations. Training from image captions with grounded bounding boxes (ground truth or pseudo-labeled) enable the models
Visual question answering (VQA) has traditionally been treated as a single-step task where each question receives the same amount of effort, unlike natural human question-answering strategies. We explore a question decomposition strategy for VQA to overcome this limitation. We probe the ability of recently
Although planning is a crucial component of the autonomous driving stack, researchers have yet to develop robust planning algorithms that are capable of safely handling the diverse range of possible driving scenarios. Learning-based planners suffer from overfitting and poor long-tail performance. On
For example, in machine translation tasks, to achieve bidirectional translation between two languages, the source corpus is often used as the target corpus, which involves the training of two models with opposite directions. The question of which one can adapt most quickly to a domain shift is of significant
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:
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
Large language models (LLMs) have significantly advanced the field of natural language processing (NLP), providing a highly useful, task agnostic foundation for a wide range of applications. The great promise of LLMs as general task solvers motivated people to extend their functionality largely beyond
It has been demonstrated that prompt tuning is highly effective in efficiently eliciting knowledge from language models (LMs). However, the prompt tuning still lags behind fine tuning, especially when the LMs are small. P tuning v2 (Liu et al., 2021b) makes it comparable with finetuning by adding continuous
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
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
Learning transferable and domain adaptive feature representations from videos is important for video-relevant tasks such as action recognition. Existing video domain adaptation methods mainly rely on adversarial feature alignment, which has been derived from the RGB image space. However, video data is
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
We address the problem of domain adaptation in videos for the task of human action recognition. Inspired by image-based domain adaptation, we can perform video adaptation by aligning the features of frames or clips of source and target videos. However, equally aligning all clips is sub-optimal as not
In this paper, we address the problem of inferring the layout of complex road scenes from video sequences. To this end, we formulate it as a top-view road attributes prediction problem and our goal is to predict these attributes for each frame both accurately and consistently. In contrast to prior work,
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 address the problem of human action classification in drone videos. Due to the high cost of capturing and labeling large-scale drone videos with diverse actions, we present unsupervised and semi-supervised domain adaptation approaches that leverage both the existing fully annotated action recognition
Read Deep Supervision with Intermediate Concepts (IEEE). Recent data-driven approaches to scene interpretation predominantly pose inference as an end-to-end black-box mapping, commonly performed by a Convolutional Neural Network (CNN). However, decades of work on perceptual organization in both human
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
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
