SOTAVerified

Video Grounding

Video grounding is the task of linking spoken language descriptions to specific video segments. In video grounding, the model is given a video and a natural language description, such as a sentence or a caption, and its goal is to identify the specific segment of the video that corresponds to the description. This can involve tasks such as localizing the objects or actions mentioned in the description within the video, or associating a specific time interval with the description.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 114 papers

TitleStatusHype
InternVideo2: Scaling Foundation Models for Multimodal Video UnderstandingCode7
Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video UnderstandingCode4
SnAG: Scalable and Accurate Video GroundingCode4
Query-Dependent Video Representation for Moment Retrieval and Highlight DetectionCode2
Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment RetrievalCode2
VTimeLLM: Empower LLM to Grasp Video MomentsCode2
Context-Guided Spatio-Temporal Video GroundingCode2
Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data EfficiencyCode2
UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight DetectionCode2
LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal UnderstandingCode2
PG-Video-LLaVA: Pixel Grounding Large Video-Language ModelsCode2
TimeZero: Temporal Video Grounding with Reasoning-Guided LVLMCode2
Human-centric Spatio-Temporal Video Grounding With Visual TransformersCode1
HawkEye: Training Video-Text LLMs for Grounding Text in VideosCode1
Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video GroundingCode1
Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form SentencesCode1
Knowing Where to Focus: Event-aware Transformer for Video GroundingCode1
Grounded Question-Answering in Long Egocentric VideosCode1
TubeDETR: Spatio-Temporal Video Grounding with TransformersCode1
VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video CaptioningCode1
Text-Visual Prompting for Efficient 2D Temporal Video GroundingCode1
Detecting Moments and Highlights in Videos via Natural Language QueriesCode1
VLG-Net: Video-Language Graph Matching Network for Video GroundingCode1
Weakly-Supervised Temporal Article GroundingCode1
Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video GroundingCode1
CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal GroundingCode1
Dense Regression Network for Video GroundingCode1
TimeLoc: A Unified End-to-End Framework for Precise Timestamp Localization in Long VideosCode1
VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction FormatCode1
Gaussian Mixture Proposals with Pull-Push Learning Scheme to Capture Diverse Events for Weakly Supervised Temporal Video GroundingCode1
OmniSTVG: Toward Spatio-Temporal Omni-Object Video GroundingCode1
Can I Trust Your Answer? Visually Grounded Video Question AnsweringCode1
Localizing Moments in Long Video Via Multimodal GuidanceCode1
Animal Kingdom: A Large and Diverse Dataset for Animal Behavior UnderstandingCode1
Negative Sample Matters: A Renaissance of Metric Learning for Temporal GroundingCode1
Explore-And-Match: Bridging Proposal-Based and Proposal-Free With Transformer for Sentence Grounding in VideosCode1
Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight DetectionCode1
DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long VideosCode1
Object-Shot Enhanced Grounding Network for Egocentric VideoCode1
VidLanKD: Improving Language Understanding via Video-Distilled Knowledge TransferCode1
EVOQUER: Enhancing Temporal Grounding with Video-Pivoted BackQuery Generation—0
EtC: Temporal Boundary Expand then Clarify for Weakly Supervised Video Grounding with Multimodal Large Language Model—0
Enhancing Weakly Supervised Video Grounding via Diverse Inference Strategies for Boundary and Prediction Selection—0
End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding—0
SynopGround: A Large-Scale Dataset for Multi-Paragraph Video Grounding from TV Dramas and Synopses—0
Multi-Scale Self-Contrastive Learning with Hard Negative Mining for Weakly-Supervised Query-based Video Grounding—0
End-to-End Dense Video Grounding via Parallel Regression—0
Collaborative Static and Dynamic Vision-Language Streams for Spatio-Temporal Video Grounding—0
Iterative Proposal Refinement for Weakly-Supervised Video Grounding—0
DiffusionVMR: Diffusion Model for Joint Video Moment Retrieval and Highlight Detection—0
Show:102550
← PrevPage 1 of 3Next →
All datasetsQVHighlightsMAD

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1InternVideo2-6BR@1,IoU=0.756.45—Unverified
2InternVideo2-1BR@1,IoU=0.754.45—Unverified
3LLMEPETR@1,IoU=0.749.94—Unverified
4QD-DETRR@1,IoU=0.744.98—Unverified
5DiffusionVMRR@1,IoU=0.744.49—Unverified
6UMTR@1,IoU=0.741.18—Unverified
7Moment-DETRR@1,IoU=0.733.02—Unverified
#ModelMetricClaimedVerifiedStatus
1DeCafNetR@1,IoU=0.113.25—Unverified
2DenoiseLocR@1,IoU=0.111.59—Unverified