Computer Vision

CLEVRER: The first video dataset for neuro-symbolic reasoning

Reasoning about Human-Object Interactions through Dual Attention Networks

LaSO: Label-Set Operations networks for multi-label few-shot learning

SpotTune: Transfer Learning through Adaptive Fine-tuning

RepMet: Representative-based metric learning for classification and one-shot object detection

ObjectNet: A bias-controlled dataset object recognition

Moments in Time Dataset: one million videos for event understanding

Self-supervised Moving Vehicle Tracking with Stereo Sound

The sound of motions

TSM: Temporal Shift Module for Efficient Video Understanding

Graph Convolutional Networks for Temporal Action Localization

Big-Little-Video-Net: Work smarter, not harder, for video understanding

Cross-channel Communication Networks

Watch, Reason and Code: Learning to Represent Videos Using Program

Facial Image-to-Video Translation by a Hidden Affine Transformation

Local Unsupervised Learning for Image Analysis

Beyond RNNs: Positional Self-Attention with Co-Attention for Video Question Answering

The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision

Revisiting RCNN: On Awakening the Classification Power of Faster RCNN

Weakly Supervised Dense Event Captioning in Videos

StNet: Local and Global Spatial-Temporal Modeling for Action Recognition

Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding

Delta-encoder: an effective sample synthesis method for few-shot object recognition

Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation

Dialog-based Interactive Image Retrieval

The Sound of Pixels

Learning to Separate Object Sounds by Watching Unlabeled Video

BlockDrop: Dynamic Inference Paths in Residual Networks