Media Analytics

Read our publications from our Media Analytics team who are overcoming fundamental challenges in computer vision and are addressing critical needs in mobility, security, safety and socially relevant AI. Our team solves fundamental challenges in computer vision, with a focus on understanding and interaction in 3D scenes, representation learning in visual and multimodal data, learning across domains and tasks, as well as responsible AI. Our technological breakthroughs contribute to socially-relevant solutions that address key enterprise needs in mobility, safety and smart spaces.

Posts

SMART: Simultaneous Multi-Agent Recurrent Trajectory Prediction

We propose advances that address two key challenges in future trajectory prediction: (i) multimodality in both training data and predictions and (ii) constant time inference regardless of number of agents. Existing trajectory predictions are fundamentally limited by lack of diversity in training data, which is difficult to acquire with sufficient coverage of possible modes. Our first contribution is an automatic method to simulate diverse trajectories in the top-view. It uses pre-existing datasets and maps as initialization, mines existing trajectories to represent realistic driving behaviors and uses a multi-agent vehicle dynamics simulator to generate diverse new trajectories that cover various modes and are consistent with scene layout constraints. Our second contribution is a novel method that generates diverse predictions while accounting for scene semantics and multi-agent interactions, with constant-time inference independent of the number of agents. We propose a convLSTM with novel state pooling operations and losses to predict scene-consistent states of multiple agents in a single forward pass, along with a CVAE for diversity. We validate our proposed multi-agent trajectory prediction approach by training and testing on the proposed simulated dataset and existing real datasets of traffic scenes. In both cases, our approach outperforms SOTA methods by a large margin, highlighting the benefits of both our diverse dataset simulation and constant-time diverse trajectory prediction methods.”

Improving Face Recognition by Clustering Unlabeled Faces in the Wild (arXiv)

Read Improving Face Recognition by Clustering Unlabeled Faces in the Wild (arXiv). While deep face recognition has benefited significantly from large scale labeled data, current research is focused on leveraging unlabeled data to further boost performance, reducing the cost of human annotation. Prior work has mostly been in controlled settings, where the labeled and unlabeled data sets have no overlapping identities by construction. This is not realistic in large scale face recognition, where one must contend with such overlaps, the frequency of which increases with the volume of data. Ignoring identity overlap leads to significant labeling noise, as data from the same identity is split into multiple clusters. To address this, we propose a novel identity separation method based on extreme value theory. It is formulated as an out of distribution detection algorithm, and greatly reduces the problems caused by overlapping identity label noise. Considering cluster assignments as pseudo labels, we must also overcome the labeling noise from clustering errors. We propose a modulation of the cosine loss, where the modulation weights correspond to an estimate of clustering uncertainty. Extensive experiments on both controlled and real settings demonstrate our method’s consistent improvements over supervised baselines, e.g., 11.6% improvement on IJB A verification.

Peek-a-boo: Occlusion Reasoning in Indoor Scenes with Plane Representations

We address the challenging task of occlusion-aware indoor 3D scene understanding. We represent scenes by a set of planes, where each one is defined by its normal, offset and two masks outlining (i) the extent of the visible part and (ii) the full region that consists of both visible and occluded parts of the plane. We infer these planes from a single input image with a novel neural network architecture. It consists of a two-branch category-specific module that aims to predict layout and objects of the scene separately so that different types of planes can be handled better. We also introduce a novel loss function based on plane warping that can leverage multiple views at training time for improved occlusion-aware reasoning. In order to train and evaluate our occlusion-reasoning model, we use the ScanNet dataset and propose (i) a strategy to automatically extract ground truth for both visible and hidden regions and (ii) a new evaluation metric that specifically focuses on the prediction in hidden regions. We empirically demonstrate that our proposed approach can achieve higher accuracy for occlusion reasoning compared to competitive baselines on the ScanNet dataset, e.g. 42.65% relative improvement on hidden regions.

Private-kNN Practical Differential Privacy for Computer Vision

With increasing ethical and legal concerns on privacy for deep models in visual recognition, differential privacy has emerged as a mechanism to disguise membership of sensitive data in training datasets. Recent methods like Private Aggregation of Teacher Ensembles (PATE) leverage a large ensemble of teacher models trained on disjoint subsets of private data, to transfer knowledge to a student model with privacy guarantees. However, labeled vision data is often expensive and datasets, when split into many disjoint training sets, lead to significantly sub-optimal accuracy and thus hardly sustain good privacy bounds. We propose a practically data-efficient scheme based on private release of k-nearest neighbor (kNN) queries, which altogether avoids splitting the training dataset. Our approach allows the use of privacy-amplification by subsampling and iterative refinement of the kNN feature embedding. We rigorously analyze the theoretical properties of our method and demonstrate strong experimental performance on practical computer vision datasets for face attribute recognition and person reidentification. In particular, we achieve comparable or better accuracy than PATE while reducing more than 90% of the privacy loss, thereby providing the “most practical method to-date” for private deep learning in computer vision.

Towards Universal Representation Learning for Deep Face Recognition

Recognizing wild faces is extremely hard as they appear with all kinds of variations. Traditional methods either train with specifically annotated variation data from target domains, or by introducing unlabeled target variation data to adapt from the training data. Instead, we propose a universal representation learning framework that can deal with larger variation unseen in the given training data without leveraging target domain knowledge. We firstly synthesize training data alongside some semantically meaningful variations, such as low resolution, occlusion and head pose. However, directly feeding the augmented data for training will not converge well as the newly introduced samples are mostly hard examples. We propose to split the feature embedding into multiple sub-embeddings, and associate different confidence values for each sub-embedding to smooth the training procedure. The sub-embeddings are further decorrelated by regularizing variation classification loss and variation adversarial loss on different partitions of them. Experiments show that our method achieves top performance on general face recognition datasets such as LFW and MegaFace, while significantly better on extreme benchmarks such as TinyFace and IJB-S.

Understanding Road Layout from Videos as a Whole

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 exploit the following three novel aspects: leveraging camera motions in videos, including context cues and incorporating long-term video information. Specifically, we introduce a model that aims to enforce prediction consistency in videos. Our model consists of one LSTM and one Feature Transform Module (FTM). The former implicitly incorporates the consistency constraint with its hidden states, and the latter explicitly takes the camera motion into consideration when aggregating information along videos. Moreover, we propose to incorporate context information by introducing road participants, e.g. objects, into our model. When the entire video sequence is available, our model is also able to encode both local and global cues, e.g. information from both past and future frames. Experiments on two data sets show that: (1) Incorporating either global or contextual cues improves the prediction accuracy and leveraging both gives the best performance. (2) Introducing the LSTM and FTM modules improves the prediction consistency in videos. (3) The proposed method outperforms the SOTA by a large margin.

Active Adversarial Domain Adaptation

We propose an active learning approach for transferring representations across domains. Our approach, active adversarial domain adaptation (AADA), explores a duality between two related problems: adversarial domain alignment and importance sampling for adapting models across domains. The former uses a domain discriminative model to align domains, while the latter utilizes the model to weigh samples to account for distribution shifts. Specifically, our importance weight promotes unlabeled samples with large uncertainty in classification and diversity compared to la-beled examples, thus serving as a sample selection scheme for active learning. We show that these two views can be unified in one framework for domain adaptation and transfer learning when the source domain has many labeled examples while the target domain does not. AADA provides significant improvements over fine-tuning based approaches and other sampling methods when the two domains are closely related. Results on challenging domain adaptation tasks such as object detection demonstrate that the advantage over baseline approaches is retained even after hundreds of examples being actively annotated.

Coordinated Joint Multimodal Embeddings for Generalized Audio-Visual Zero-shot Classification and Retrieval of Videos

We present an audio-visual multimodal approach for the task of zero-shot learning (ZSL) for classification and retrieval of videos. ZSL has been studied extensively in the recent past but has primarily been limited to visual modality and to images. We demonstrate that both audio and visual modalities are important for ZSL for videos. Since a dataset to study the task is currently not available, we also construct an appropriate multimodal dataset with 33 classes containing 156, 416 videos, from an existing large scale audio event dataset. We empirically show that the performance improves by adding audio modality for both tasks of zero-shot classification and retrieval, when using multi-modal extensions of embedding learning methods. We also propose a novel method to predict the `dominant’ modality using a jointly learned modality attention network. We learn the attention in a semi-supervised setting and thus do not require any additional explicit labelling for the modalities. We provide qualitative validation of the modality specific attention, which also successfully generalizes to unseen test classes.

DAVID: Dual-Attentional Video Deblurring

Blind video deblurring restores sharp frames from a blurry sequence without any prior. It is a challenging task because the blur due to camera shake, object movement and defocusing is heterogeneous in both temporal and spatial dimensions. Traditional methods train on datasets synthesized with a single level of blur, and thus do not generalize well across levels of blurriness. To address this challenge, we propose a dual attention mechanism to dynamically aggregate temporal cues for deblurring with an end-to-end trainable network structure. Specifically, an internal attention module adaptively selects the optimal temporal scales for restoring the sharp center frame. An external attention module adaptively aggregates and refines multiple sharp frame estimates, from several internal attention modules designed for different blur levels. To train and evaluate on more diverse blur severity levels, we propose a Challenging DVD dataset generated from the raw DVD video set by pooling frames with different temporal windows. Our framework achieves consistently better performance on this more challenging dataset while obtaining strongly competitive results on the original DVD benchmark. Extensive ablative studies and qualitative visualizations further demonstrate the advantage of our method in handling real video blur.

Unsupervised and Semi-Supervised Domain Adaptation for Action Recognition from Drones

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 datasets and unannotated (or only a few annotated) videos from drones. To study the emerging problem of drone-based action recognition, we create a new dataset, NEC-DRONE, containing 5,250 videos to evaluate the task. We tackle both problem settings with 1) same and 2) different action label sets for the source (e.g., Kinectics dataset) and target domains (drone videos). We present a combination of video and instance-based adaptation methods, paired with either a classifier or an embedding-based framework to transfer the knowledge from source to target. Our results show that the proposed adaptation approach substantially improves the performance on these challenging and practical tasks. We further demonstrate the applicability of our method for learning cross-view action recognition on the Charades-Ego dataset. We provide qualitative analysis to understand the behaviors of our approaches.