Video Understanding
State-of-the-art leaderboards
Greatest papers with code
AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions
CVPR 2018
• tensorflow/models
• 
The AVA dataset densely annotates 80 atomic visual actions in 430 15-minute video clips, where actions are localized in space and time, resulting in 1.58M action labels with multiple labels per person occurring frequently. The key characteristics of our dataset are: (1) the definition of atomic visual actions, rather than composite actions; (2) precise spatio-temporal annotations with possibly multiple annotations for each person; (3) exhaustive annotation of these atomic actions over 15-minute video clips; (4) people temporally linked across consecutive segments; and (5) using movies to gather a varied set of action representations.
TS-LSTM and Temporal-Inception: Exploiting Spatiotemporal Dynamics for Activity Recognition
• chihyaoma/Activity-Recognition-with-CNN-and-RNN
• 
Building upon our experimental results, we then propose and investigate two different networks to further integrate spatiotemporal information: 1) temporal segment RNN and 2) Inception-style Temporal-ConvNet. We demonstrate that using both RNNs (using LSTMs) and Temporal-ConvNets on spatiotemporal feature matrices are able to exploit spatiotemporal dynamics to improve the overall performance.
ACTION CLASSIFICATION ACTIVITY RECOGNITION VIDEO CLASSIFICATION VIDEO UNDERSTANDING
Learnable pooling with Context Gating for video classification
• antoine77340/Youtube-8M-WILLOW
•
Current methods for video analysis often extract frame-level features using pre-trained convolutional neural networks (CNNs). In particular, we evaluate our method on the large-scale multi-modal Youtube-8M v2 dataset and outperform all other methods in the Youtube 8M Large-Scale Video Understanding challenge.
ECO: Efficient Convolutional Network for Online Video Understanding
ECCV 2018
• mzolfaghari/ECO-efficient-video-understanding
• 
The state of the art in video understanding suffers from two problems: (1) The major part of reasoning is performed locally in the video, therefore, it misses important relationships within actions that span several seconds. In this paper, we introduce a network architecture that takes long-term content into account and enables fast per-video processing at the same time.
The Monkeytyping Solution to the YouTube-8M Video Understanding Challenge
This article describes the final solution of team monkeytyping, who finished in second place in the YouTube-8M video understanding challenge. The dataset used in this challenge is a large-scale benchmark for multi-label video classification.
Temporal Tessellation: A Unified Approach for Video Analysis
ICCV 2017
• dot27/temporal-tessellation
•
We present a general approach to video understanding, inspired by semantic transfer techniques that have been successfully used for 2D image analysis. A test video is processed by forming correspondences between its clips and the clips of reference videos with known semantics, following which, reference semantics can be transferred to the test video.
ACTION DETECTION VIDEO CAPTIONING VIDEO SUMMARIZATION VIDEO UNDERSTANDING
Learnable Pooling Methods for Video Classification
• pomonam/LearnablePoolingMethods
Rather than using ensembles of existing architectures, we provide an insight on creating new architectures. We demonstrate our solutions in the "The 2nd YouTube-8M Video Understanding Challenge", by using frame-level video and audio descriptors.
Watch, Listen, and Describe: Globally and Locally Aligned Cross-Modal Attentions for Video Captioning
HLT 2018
• chitwansaharia/HACAModel
•
Existing multi-modal fusion methods have shown encouraging results in video understanding. Furthermore, for the first time, we validate the superior performance of the deep audio features on the video captioning task.
Pooled Motion Features for First-Person Videos
CVPR 2015 • mryoo/pooled_time_series
In this paper, we present a new feature representation for first-person videos. We also confirm that our feature representation has superior performance to existing state-of-the-art features like local spatio-temporal features and Improved Trajectory Features (originally developed for 3rd-person videos) when handling first-person videos.
Temporal Shift Module for Efficient Video Understanding
• PaParaZz1/TemporalShiftModule
•
The explosive growth in online video streaming gives rise to challenges on efficiently extracting the spatial-temporal information to perform video understanding. Specifically, it can achieve the performance of 3D CNN but maintain 2D complexity.