SOTAVerified

Action Localization

Action Localization is finding the spatial and temporal co ordinates for an action in a video. An action localization model will identify which frame an action start and ends in video and return the x,y coordinates of an action. Further the co ordinates will change when the object performing action undergoes a displacement.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–125 of 369 papers

TitleStatusHype
Multi-modal Prompting for Low-Shot Temporal Action Localization—0
TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action LocalizationCode1
Co-Occurrence Matters: Learning Action Relation for Temporal Action Localization—0
Faster Learning of Temporal Action Proposal via Sparse Multilevel Boundary GeneratorCode0
Temporal Perceiving Video-Language Pre-training—0
Ego-Only: Egocentric Action Detection without Exocentric Transferring—0
Anchor-free temporal action localization via Progressive Boundary-aware BoostingCode0
Boosting Positive Segments for Weakly-Supervised Audio-Visual Video ParsingCode0
Learning from Noisy Pseudo Labels for Semi-Supervised Temporal Action LocalizationCode0
Few-Shot Common Action Localization via Cross-Attentional Fusion of Context and Temporal Dynamics—0
Chaotic World: A Large and Challenging Benchmark for Human Behavior Understanding in Chaotic EventsCode1
Two-Stream Networks for Weakly-Supervised Temporal Action Localization With Semantic-Aware Mechanisms—0
Cascade Evidential Learning for Open-World Weakly-Supervised Temporal Action Localization—0
AdamsFormer for Spatial Action Localization in the Future—0
Re2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action LocalizationCode0
PivoTAL: Prior-Driven Supervision for Weakly-Supervised Temporal Action Localization—0
Distilling Vision-Language Pre-training to Collaborate with Weakly-Supervised Temporal Action Localization—0
Dilation-Erosion for Single-Frame Supervised Temporal Action LocalizationCode0
Re^2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action LocalizationCode1
Slow Motion Matters: A Slow Motion Enhanced Network for Weakly Supervised Temporal Action Localization—0
ReLER@ZJU Submission to the Ego4D Moment Queries Challenge 2022Code0
Where a Strong Backbone Meets Strong Features -- ActionFormer for Ego4D Moment Queries ChallengeCode2
A Simple Transformer-Based Model for Ego4D Natural Language Queries ChallengeCode0
Soft-Landing Strategy for Alleviating the Task Discrepancy Problem in Temporal Action Localization TasksCode0
Prior-enhanced Temporal Action Localization using Subject-aware Spatial Attention—0
Show:102550
← PrevPage 5 of 15Next →

No leaderboard results yet.