research
∙
06/06/2023
Energy-Based Models for Cross-Modal Localization using Convolutional Transformers
We present a novel framework using Energy-Based Models (EBMs) for locali...
share
research
∙
06/01/2023
Active Reinforcement Learning under Limited Visual Observability
In this work, we investigate Active Reinforcement Learning (Active-RL), ...
research
∙
04/05/2023
VicTR: Video-conditioned Text Representations for Activity Recognition
Vision-Language models have shown strong performance in the image-domain...
research
∙
11/16/2022
Token Turing Machines
We propose Token Turing Machines (TTM), a sequential, autoregressive Tra...
research
∙
10/28/2022
Grafting Vision Transformers
Vision Transformers (ViTs) have recently become the state-of-the-art acr...
research
∙
08/01/2022
Video Question Answering with Iterative Video-Text Co-Tokenization
Video question answering is a challenging task that requires understandi...
research
∙
07/01/2022
Video + CLIP Baseline for Ego4D Long-term Action Anticipation
In this report, we introduce our adaptation of image-text models for lon...
research
∙
06/23/2022
Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space
Humans are remarkably flexible in understanding viewpoint changes due to...
research
∙
12/07/2021
STC-mix: Space, Time, Channel mixing for Self-supervised Video Representation
Contrastive representation learning of videos highly relies on the avail...
research
∙
12/07/2021
ViewCLR: Learning Self-supervised Video Representation for Unseen Viewpoints
Learning self-supervised video representation predominantly focuses on d...
research
∙
12/07/2021
MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection
Action detection is an essential and challenging task, especially for de...
research
∙
11/26/2021
SWAT: Spatial Structure Within and Among Tokens
Modeling visual data as tokens (i.e., image patches), and applying atten...
research
∙
11/26/2021
Self-supervised Pretraining with Classification Labels for Temporal Activity Detection
Temporal Activity Detection aims to predict activity classes per frame, ...
research
∙
10/12/2021
StARformer: Transformer with State-Action-Reward Representations
Reinforcement Learning (RL) can be considered as a sequence modeling tas...
research
∙
10/08/2021
Hybrid Random Features
We propose a new class of random feature methods for linearizing softmax...
research
∙
09/02/2021
4D-Net for Learned Multi-Modal Alignment
We present 4D-Net, a 3D object detection approach, which utilizes 3D Poi...
research
∙
08/02/2021
Self-Supervised Disentangled Representation Learning for Third-Person Imitation Learning
Humans learn to imitate by observing others. However, robot imitation le...
research
∙
06/28/2021
Unsupervised Discovery of Actions in Instructional Videos
In this paper we address the problem of automatically discovering atomic...
research
∙
06/21/2021
TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?
In this paper, we introduce a novel visual representation learning which...
research
∙
06/07/2021
Unsupervised Action Segmentation for Instructional Videos
In this paper we address the problem of automatically discovering atomic...
research
∙
03/30/2021
Recognizing Actions in Videos from Unseen Viewpoints
Standard methods for video recognition use large CNNs designed to captur...
research
∙
03/26/2021
Visionary: Vision architecture discovery for robot learning
We propose a vision-based architecture search algorithm for robot manipu...
research
∙
03/01/2021
Coarse-Fine Networks for Temporal Activity Detection in Videos
In this paper, we introduce 'Coarse-Fine Networks', a two-stream archite...
research
∙
11/13/2020
Reducing Inference Latency with Concurrent Architectures for Image Recognition
Satisfying the high computation demand of modern deep learning architect...
research
∙
08/18/2020
AssembleNet++: Assembling Modality Representations via Attention Connections
We create a family of powerful video models which are able to: (i) learn...
research
∙
08/11/2020
Adversarial Generative Grammars for Human Activity Prediction
In this paper we propose an adversarial generative grammar model for fut...
research
∙
07/23/2020
AttentionNAS: Spatiotemporal Attention Cell Search for Video Classification
Convolutional operations have two limitations: (1) do not explicitly mod...
research
∙
07/10/2020
AViD Dataset: Anonymized Videos from Diverse Countries
We introduce a new public video dataset for action recognition: Anonymiz...
research
∙
03/13/2020
Edge-Tailored Perception: Fast Inferencing in-the-Edge with Efficient Model Distribution
The rise of deep neural networks (DNNs) is inspiring new studies in myri...
research
∙
02/26/2020
Evolving Losses for Unsupervised Video Representation Learning
We present a new method to learn video representations from large-scale ...
research
∙
11/26/2019
Password-conditioned Anonymization and Deanonymization with Face Identity Transformers
Cameras are prevalent in our daily lives, and enable many useful systems...
research
∙
10/15/2019
Tiny Video Networks
Video understanding is a challenging problem with great impact on the ab...
research
∙
10/08/2019
Model-based Behavioral Cloning with Future Image Similarity Learning
We present a visual imitation learning framework that enables learning o...
research
∙
06/07/2019
Evolving Losses for Unlabeled Video Representation Learning
We present a new method to learn video representations from unlabeled da...
research
∙
05/30/2019
AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures
Learning to represent videos is a very challenging task both algorithmic...
research
∙
04/18/2019
Early Detection of Injuries in MLB Pitchers from Video
Injuries are a major cost in sports. Teams spend millions of dollars eve...
research
∙
02/01/2019
Learning Differentiable Grammars for Continuous Data
This paper proposes a novel algorithm which learns a formal regular gram...
research
∙
11/26/2018
Evolving Space-Time Neural Architectures for Videos
In this paper, we present a new method for evolving video CNN models to ...
research
∙
10/02/2018
Representation Flow for Action Recognition
In this paper, we propose a convolutional layer inspired by optical flow...
research
∙
06/21/2018
Learning Shared Multimodal Embeddings with Unpaired Data
In this paper, we propose a method to learn a joint multimodal embedding...
research
∙
05/20/2018
Learning Real-World Robot Policies by Dreaming
Learning to control robots directly based on images is a primary challen...
research
∙
04/09/2018
Fine-grained Activity Recognition in Baseball Videos
In this paper, we introduce a challenging new dataset, MLB-YouTube, desi...
research
∙
03/30/2018
Learning to Anonymize Faces for Privacy Preserving Action Detection
There is an increasing concern in computer vision devices invading the p...
research
∙
03/29/2018
Joint Person Segmentation and Identification in Synchronized First- and Third-person Videos
In a world in which cameras are becoming more and more pervasive, scenes...
research
∙
03/16/2018
Activity Detection with Latent Sub-event Hierarchy Learning
In this paper, we introduce a new convolutional layer named the Temporal...
research
∙
12/05/2017
Learning Latent Super-Events to Detect Multiple Activities in Videos
In this paper, we introduce the concept of learning latent super-events ...
research
∙
08/03/2017
Extreme Low Resolution Activity Recognition with Multi-Siamese Embedding Learning
This paper presents an approach for recognition of human activities from...
research
∙
05/20/2017
Forecasting Hands and Objects in Future Frames
This paper presents an approach to forecast future presence and location...
research
∙
03/03/2017
Learning Robot Activities from First-Person Human Videos Using Convolutional Future Regression
We design a new approach that allows robot learning of new activities fr...
research
∙
03/01/2017