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

Showing 110 of 486 papers

TitleStatusHype
MAGMaR Shared Task System Description: Video Retrieval with OmniEmbed0
Q2E: Query-to-Event Decomposition for Zero-Shot Multilingual Text-to-Video Retrieval0
From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained VideosCode0
Leveraging Auxiliary Information in Text-to-Video Retrieval: A Review0
Learning World Models for Interactive Video Generation0
A Challenge to Build Neuro-Symbolic Video AgentsCode0
LoVR: A Benchmark for Long Video Retrieval in Multimodal ContextsCode1
Contrastive Alignment with Semantic Gap-Aware Corrections in Text-Video RetrievalCode0
Video-GPT via Next Clip DiffusionCode1
CMAWRNet: Multiple Adverse Weather Removal via a Unified Quaternion Neural Architecture0
Show:102550
← PrevPage 1 of 49Next →

Benchmark Results

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