Streamlined Dense Video Captioning

InstaGAN: Instance-aware Image-to-Image Translation

Forget & Diversify: Regularized Refinement for Weakly Supervised Object Detection

Universal Bounding Box Regression and Its Applications

Learning to Specialize with Knowledge Distillation for Visual Question Answering

Video Understanding via Convolutional Temporal Pooling Network and Multimodal Feature Fusion

CPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of Maps

Attentive Semantic Alignment with Offset-Aware Correlation Kernels

Real-Time MDNet

First Person Action Recognition via Two-stream ConvNet with Long-term Fusion Pooling