SOTAVerified

Video Understanding

A crucial task of Video Understanding is to recognise and localise (in space and time) different actions or events appearing in the video.

Source: Action Detection from a Robot-Car Perspective

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1051–1100 of 1149 papers

TitleStatusHype
Representation Learning on Visual-Symbolic Graphs for Video Understanding—0
Video Instance SegmentationCode2
Large Scale Holistic Video UnderstandingCode1
Recurrent Space-time Graph Neural NetworksCode0
Constructing Hierarchical Q&A Datasets for Video Story Understanding—0
Wasserstein Dependency Measure for Representation Learning—0
4D Generic Video Object ProposalsCode0
DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition—0
Future semantic segmentation of time-lapsed videos with large temporal displacement—0
Dynamic Graph Modules for Modeling Object-Object Interactions in Activity Recognition—0
Long-Term Feature Banks for Detailed Video UnderstandingCode0
A Structured Model For Action Detection—0
An Attempt towards Interpretable Audio-Visual Video Captioning—0
The Visual Centrifuge: Model-Free Layered Video RepresentationsCode0
How to Make a BLT Sandwich? Learning to Reason towards Understanding Web Instructional Videos—0
Self-Supervised Spatiotemporal Feature Learning via Video Rotation Prediction—0
Integrated Object Detection and Tracking with Tracklet-Conditioned Detection—0
Efficient Video Understanding via Layered Multi Frame-Rate Analysis—0
TSM: Temporal Shift Module for Efficient Video UnderstandingCode1
NeXtVLAD: An Efficient Neural Network to Aggregate Frame-level Features for Large-scale Video ClassificationCode0
Random Temporal Skipping for Multirate Video Analysis—0
Morph: Flexible Acceleration for 3D CNN-based Video Understanding—0
Unsupervised Adversarial Visual Level Domain Adaptation for Learning Video Object Detectors from ImagesCode0
Representation Flow for Action RecognitionCode0
Learnable Pooling Methods for Video ClassificationCode0
Non-local NetVLAD Encoding for Video Classification—0
Large-Scale Video Classification with Feature Space Augmentation coupled with Learned Label Relations and Ensembling—0
Label Denoising with Large Ensembles of Heterogeneous Neural Networks—0
Localizing Moments in Video with Temporal LanguageCode0
End-to-End Joint Semantic Segmentation of Actors and Actions in Video—0
Teaching Machines to Understand Baseball Games: Large-Scale Baseball Video Database for Multiple Video Understanding Tasks—0
Constrained-size Tensorflow Models for YouTube-8M Video Understanding ChallengeCode0
Diagnosing Error in Temporal Action DetectorsCode0
Video Time: Properties, Encoders and Evaluation—0
Query-Conditioned Three-Player Adversarial Network for Video Summarization—0
When Work Matters: Transforming Classical Network Structures to Graph CNN—0
Deep Spatio-Temporal Random Fields for Efficient Video Segmentation—0
Long Activity Video Understanding using Functional Object-Oriented Network—0
Exploiting Spatial-Temporal Modelling and Multi-Modal Fusion for Human Action Recognition—0
VirtualHome: Simulating Household Activities via ProgramsCode1
Massively Parallel Video Networks—0
Geometry Guided Convolutional Neural Networks for Self-Supervised Video Representation Learning—0
What Makes a Video a Video: Analyzing Temporal Information in Video Understanding Models and Datasets—0
DenseImage Network: Video Spatial-Temporal Evolution Encoding and Understanding—0
Fast Retinomorphic Event Stream for Video Recognition and Reinforcement Learning—0
Dilated Temporal Relational Adversarial Network for Generic Video Summarization—0
Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videos—0
ECO: Efficient Convolutional Network for Online Video UnderstandingCode0
Watch, Listen, and Describe: Globally and Locally Aligned Cross-Modal Attentions for Video CaptioningCode0
End-to-End Learning of Motion Representation for Video UnderstandingCode0
Show:102550
← PrevPage 22 of 23Next →

No leaderboard results yet.