SOTAVerified

Situation Recognition

Situation Recognition aims to produce the structured image summary which describes the primary activity (verb), and its relevant entities (nouns).

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–12 of 12 papers

TitleStatusHype
Dynamic Scene Understanding from Vision-Language Representations—0
ClipSitu: Effectively Leveraging CLIP for Conditional Predictions in Situation RecognitionCode0
Collaborative Transformers for Grounded Situation RecognitionCode1
Rethinking the Two-Stage Framework for Grounded Situation RecognitionCode1
Grounded Situation Recognition with TransformersCode1
Attention-Based Context Aware Reasoning for Situation RecognitionCode1
Grounded Situation RecognitionCode1
Mixture-Kernel Graph Attention Network for Situation Recognition—0
Situation Recognition with Graph Neural NetworksCode1
Recurrent Models for Situation Recognition—0
Commonly Uncommon: Semantic Sparsity in Situation RecognitionCode0
Situation Recognition: Visual Semantic Role Labeling for Image UnderstandingCode0
Show:102550

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1OursTop-1 Verb58.88—Unverified
2ClipSituTop-1 Verb47.23—Unverified
3CoFormerTop-1 Verb44.66—Unverified
4SituFormerTop-1 Verb44.2—Unverified
5Kernel GraphNetTop-1 Verb43.27—Unverified
6GSRTRTop-1 Verb40.63—Unverified
7JSLTop-1 Verb39.94—Unverified
8ISLTop-1 Verb39.36—Unverified
9CAQ + RE-VGGTop-1 Verb38.19—Unverified
10GraphNetTop-1 Verb36.72—Unverified