SOTAVerified

Video Retrieval

The objective of video retrieval is as follows: given a text query and a pool of candidate videos, select the video which corresponds to the text query. Typically, the videos are returned as a ranked list of candidates and scored via document retrieval metrics.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 486 papers

TitleStatusHype
MAGMaR Shared Task System Description: Video Retrieval with OmniEmbed—0
Q2E: Query-to-Event Decomposition for Zero-Shot Multilingual Text-to-Video Retrieval—0
From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained VideosCode0
Leveraging Auxiliary Information in Text-to-Video Retrieval: A Review—0
Learning World Models for Interactive Video Generation—0
A Challenge to Build Neuro-Symbolic Video AgentsCode0
LoVR: A Benchmark for Long Video Retrieval in Multimodal ContextsCode1
Video-GPT via Next Clip DiffusionCode1
Contrastive Alignment with Semantic Gap-Aware Corrections in Text-Video RetrievalCode0
CMAWRNet: Multiple Adverse Weather Removal via a Unified Quaternion Neural Architecture—0
Empowering Agentic Video Analytics Systems with Video Language Models—0
ReSpec: Relevance and Specificity Grounded Online Filtering for Learning on Video-Text Data StreamsCode0
Prototypes are Balanced Units for Efficient and Effective Partially Relevant Video Retrieval—0
Towards Efficient Partially Relevant Video Retrieval with Active Moment DiscoveringCode0
Towards Efficient and Robust Moment Retrieval System: A Unified Framework for Multi-Granularity Models and Temporal Reranking—0
TC-MGC: Text-Conditioned Multi-Grained Contrastive Learning for Text-Video RetrievalCode0
Leveraging Modality Tags for Enhanced Cross-Modal Video Retrieval—0
Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval—0
Enhancing Subsequent Video Retrieval via Vision-Language Models (VLMs)Code0
Long-VMNet: Accelerating Long-Form Video Understanding via Fixed Memory—0
StableFusion: Continual Video Retrieval via Frame AdaptationCode1
Quality Over Quantity? LLM-Based Curation for a Data-Efficient Audio-Video Foundation Model—0
Narrating the Video: Boosting Text-Video Retrieval via Comprehensive Utilization of Frame-Level Captions—0
LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning—0
Composed Multi-modal Retrieval: A Survey of Approaches and ApplicationsCode2
Learning to Generate Long-term Future Narrations Describing Activities of Daily Living—0
TransMamba: Fast Universal Architecture Adaption from Transformers to Mamba—0
Generative Ghost: Investigating Ranking Bias Hidden in AI-Generated Videos—0
VideoRoPE: What Makes for Good Video Rotary Position Embedding?Code3
HORUS: Multimodal Large Language Models Framework for Video Retrieval at VBS 2025—0
CaReBench: A Fine-Grained Benchmark for Video Captioning and Retrieval—0
Hierarchical Banzhaf Interaction for General Video-Language Representation LearningCode0
PolySmart @ TRECVid 2024 Medical Video Question Answering—0
Query-centric Audio-Visual Cognition Network for Moment Retrieval, Segmentation and Step-Captioning—0
Gramian Multimodal Representation Learning and AlignmentCode2
Generative Semantic Communication: Architectures, Technologies, and Applications—0
Multimodal Contextualized Support for Enhancing Video Retrieval System—0
Video-RAG: Visually-aligned Retrieval-Augmented Long Video ComprehensionCode3
ContextIQ: A Multimodal Expert-Based Video Retrieval System for Contextual AdvertisingCode0
Generating Signed Language Instructions in Large-Scale Dialogue SystemsCode0
MultiVENT 2.0: A Massive Multilingual Benchmark for Event-Centric Video Retrieval—0
Text Proxy: Decomposing Retrieval from a 1-to-N Relationship into N 1-to-1 Relationships for Text-Video RetrievalCode1
VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models—0
TokenBinder: Text-Video Retrieval with One-to-Many Alignment ParadigmCode0
Video DataFlywheel: Resolving the Impossible Data Trinity in Video-Language Understanding—0
Unfolding Videos Dynamics via Taylor Expansion—0
TempMe: Video Temporal Token Merging for Efficient Text-Video RetrievalCode1
Sync from the Sea: Retrieving Alignable Videos from Large-Scale Datasets—0
T2VIndexer: A Generative Video Indexer for Efficient Text-Video RetrievalCode1
MUSE: Mamba is Efficient Multi-scale Learner for Text-video RetrievalCode1
Show:102550
← PrevPage 1 of 10Next →
All datasetsMSR-VTT-1kADiDeMoMSR-VTTLSMDCActivityNetMSVDYouCook2FIVR-200KVATEXQuerYDSSv2-label retrievalSSv2-template retrieval

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1OmniVectext-to-video R@1089.4—Unverified
2CLIP4Cliptext-to-video R@1081.6—Unverified
3OmniVec (pretrained)text-to-video R@1078.6—Unverified
4HunYuan_tvr (huge)text-to-video R@162.9—Unverified
5CLIP-ViPtext-to-video R@157.7—Unverified
6PIDRotext-to-video R@155.9—Unverified
7DMAE (ViT-B/16)text-to-video R@155.5—Unverified
8HunYuan_tvrtext-to-video R@155—Unverified
9MuLTItext-to-video R@154.7—Unverified
10STANtext-to-video R@154.1—Unverified
#ModelMetricClaimedVerifiedStatus
1Aurora (ours, r=64)text-to-video R@577.4—Unverified
2InternVideo2-6Btext-to-video R@174.2—Unverified
3vid-TLDR (UMT-L)text-to-video R@172.3—Unverified
4VASTtext-to-video R@172—Unverified
5COSAtext-to-video R@170.5—Unverified
6UMT-L (ViT-L/16)text-to-video R@170.4—Unverified
7GRAMtext-to-video R@167.3—Unverified
8VALORtext-to-video R@161.5—Unverified
9TESTA (ViT-B/16)text-to-video R@161.2—Unverified
10VindLUtext-to-video R@161.2—Unverified
#ModelMetricClaimedVerifiedStatus
1GRAMtext-to-video R@164—Unverified
2VASTtext-to-video R@163.9—Unverified
3InternVideo2-6Btext-to-video R@162.8—Unverified
4VALORtext-to-video R@159.9—Unverified
5UMT-L (ViT-L/16)text-to-video R@158.8—Unverified
6vid-TLDR (UMT-L)text-to-video R@158.1—Unverified
7COSAtext-to-video R@157.9—Unverified
8InternVideo2-6Btext-to-video R@155.9—Unverified
9InternVideotext-to-video R@155.2—Unverified
10VLABtext-to-video R@155.1—Unverified
#ModelMetricClaimedVerifiedStatus
1EMCL-Net (Ours)++ LSMDC Rohrbach et al. (2015)text-to-video R@1053.7—Unverified
2InternVideo2-6Btext-to-video R@146.4—Unverified
3vid-TLDR (UMT-L)text-to-video R@143.1—Unverified
4UMT-L (ViT-L/16)text-to-video R@143—Unverified
5HunYuan_tvr (huge)text-to-video R@140.4—Unverified
6COSAtext-to-video R@139.4—Unverified
7mPLUG-2text-to-video R@134.4—Unverified
8VALORtext-to-video R@134.2—Unverified
9InternVideotext-to-video R@134—Unverified
10InternVideo2-6Btext-to-video R@133.8—Unverified