Video Recognition
Leaderboards
Greatest papers with code
SlowFast Networks for Video Recognition
ICCV 2019
• facebookresearch/SlowFast
• 
We present SlowFast networks for video recognition.
#2 best model for
Action Classification
on Charades
(using extra training data)
Deep Feature Flow for Video Recognition
CVPR 2017
• msracver/Deep-Feature-Flow
• 
Yet, it is non-trivial to transfer the state-of-the-art image recognition networks to videos as per-frame evaluation is too slow and unaffordable.
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
Similarly, the output feature maps of a convolution layer can also be seen as a mixture of information at different frequencies.
#22 best model for
Image Classification
on ImageNet
TSM: Temporal Shift Module for Efficient Video Understanding
ICCV 2019
• MIT-HAN-LAB/temporal-shift-module
•
The explosive growth in video streaming gives rise to challenges on performing video understanding at high accuracy and low computation cost.
ACTION RECOGNITION IN VIDEOS VIDEO OBJECT DETECTION VIDEO RECOGNITION VIDEO UNDERSTANDING
Flow-Guided Feature Aggregation for Video Object Detection
ICCV 2017
• msracver/Flow-Guided-Feature-Aggregation
•
The accuracy of detection suffers from degenerated object appearances in videos, e. g., motion blur, video defocus, rare poses, etc.
#3 best model for
Video Object Detection
on ImageNet VID
Weight Standardization
• joe-siyuan-qiao/WeightStandardization
•
The micro-batch training setting is hard because small batch sizes are not enough for training networks with Batch Normalization (BN), while other normalization methods that do not rely on batch knowledge still have difficulty matching the performances of BN in large-batch training.
IMAGE CLASSIFICATION INSTANCE SEGMENTATION OBJECT DETECTION SEMANTIC SEGMENTATION VIDEO RECOGNITION
Clockwork Convnets for Video Semantic Segmentation
Recent years have seen tremendous progress in still-image segmentation; however the na\"ive application of these state-of-the-art algorithms to every video frame requires considerable computation and ignores the temporal continuity inherent in video.
SEMANTIC SEGMENTATION VIDEO RECOGNITION VIDEO SEMANTIC SEGMENTATION
Learning Spatio-Temporal Representation with Local and Global Diffusion
Diffusions effectively interact two aspects of information, i. e., localized and holistic, for more powerful way of representation learning.
ACTION DETECTION REPRESENTATION LEARNING TEMPORAL ACTION LOCALIZATION VIDEO CLASSIFICATION VIDEO RECOGNITION
Large Scale Holistic Video Understanding
HVU is organized hierarchically in a semantic taxonomy that focuses on multi-label and multi-task video understanding as a comprehensive problem that encompasses the recognition of multiple semantic aspects in the dynamic scene.
SOTA for Multi-Task Learning on HVU
ACTION CLASSIFICATION ACTION RECOGNITION IN VIDEOS MULTI-TASK LEARNING VIDEO RECOGNITION VIDEO UNDERSTANDING
Sequence Level Semantics Aggregation for Video Object Detection
ICCV 2019
• happywu/Sequence-Level-Semantics-Aggregation
•
In this work, we argue that aggregating features in the full-sequence level will lead to more discriminative and robust features for video object detection.