Switchable Novel Object Captioner

Saying the Unseen: Video Descriptions via Dialog Agents

Learning to Anticipate Egocentric Actions by Imagination

Progressive Transfer Learning for Face Anti-Spoofing

Identifying Visible Parts via Pose Estimation for Occluded Person Re-Identification

Learning with Noisy Labels via Self-Reweighting from Class Centroids

Holistic LSTM for Pedestrian Trajectory Prediction

Symbiotic Attention for Egocentric Action Recognition with Object-centric Alignment

Unsupervised Person Re-identification via Cross-camera Similarity Exploration

Revisiting EmbodiedQA: A Simple Baseline and Beyond

Improving Person Re-identification by Attribute and Identity Learning

Progressive Learning for Person Re-Identification with One Example