PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies

Expanding Language-Image Pretrained Models for General Video Recognition

TinyViT: Fast Pretraining Distillation for Small Vision Transformers

MiniViT: Compressing Vision Transformers with Weight Multiplexing

Cyclic Differentiable Architecture Search

Multi-Scale 2D Temporal Adjacent Networks for Moment Localization with Natural Language

AutoFormerV2: Searching the Search Space of Vision Transformer

Probing Inter-modality: Visual Parsing with Self-Attention for Vision-and-Language Pre-training

Learning to Track Objects from Unlabled Videos

Rethinking and Improving Relative Position Encoding for Vision Transformer

AutoFormer: Searching Transformers for Visual Recognition

Learning Spatio-Temporal Transformer for Visual Tracking

LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search

One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinking

Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search

Ocean: Object-aware Anchor-free Tracking

A Transductive Approach for Semi-Supervised Video Object Segmentation

Learning 2D Temporal Localization Networks for Moment Localization with Natural Language

Deeper and Wider Siamese Networks for Real-time Visual Tracking

AI Coach: Deep Human Pose Estimation and Analysis for Personalized Athletic Training Assistance

Multi-view Multi-instance Learning based on Joint Sparse Representation and Multi-view Dictionary Learning

Illumination Estimation based on Bilayer Sparse Coding

Salient Object Detection via Structured Matrix Decomposition

Predicting Image Memorability by Multi-view Adaptive Regression

RGBD Salient Object Detection: A Benchmark and Algorithms

Salient Object Detection via Low-rank and Structured Sparse Matrix Decomposition