Referring Expression Segmentation On A2D

평가 지표

IoU mean

IoU overall

Precision@0.5

Precision@0.6

Precision@0.7

Precision@0.8

Precision@0.9

평가 결과

이 벤치마크에서 각 모델의 성능 결과

비교 표

모델 이름	AP	IoU mean	IoU overall	Precision@0.5	Precision@0.6	Precision@0.7	Precision@0.8	Precision@0.9
context-modulated-dynamic-networks-for-actor	0.333	0.531	0.623	0.607	0.525	0.405	0.235	0.045
actor-and-action-video-segmentation-from-a	0.215	0.426	0.551	0.5	0.376	0.231	0.094	0.004
deeply-interleaved-two-stream-encoder-for	0.469	0.598	0.714	0.702	0.663	0.585	0.428	0.151
language-as-queries-for-referring-video	0.550	0.703	0.786	0.831	0.804	0.741	0.579	0.212
collaborative-spatial-temporal-modeling-for	0.399	0.561	0.662	0.654	0.589	0.497	0.333	0.091
multi-attention-network-for-compressed-video	0.471	0.632	0.726	0.734	0.682	0.579	0.389	0.132
asymmetric-cross-guided-attention-network-for	0.274	0.490	0.601	0.557	0.459	0.319	0.16	0.02
clawcranenet-leveraging-object-level-relation	-	0.655	0.644	0.704	0.677	0.617	0.489	0.171
cross-modal-progressive-comprehension-for	0.351	0.515	0.649	0.590	0.527	0.434	0.284	0.068
soc-semantic-assisted-object-cluster-for	0.573	0.725	0.807	0.851	0.827	0.765	0.607	0.252
end-to-end-referring-video-object	0.447	0.618	0.702	0.721	0.684	0.607	0.456	0.164
refvos-a-closer-look-at-referring-expressions	-	0.599	0.599	0.495	-	-	-	0.064
actor-and-action-modular-network-for-text	0.396	0.552	0.617	0.681	0.629	0.523	0.296	0.029
cross-modal-progressive-comprehension-for	0.404	0.573	0.653	0.655	0.592	0.506	0.342	0.098
local-global-context-aware-transformer-for	0.465	0.597	0.69	0.709	0.64	0.525	0.351	0.101
visual-textual-capsule-routing-for-text-based	0.303	0.460	0.568	0.526	0.450	0.345	0.207	0.036
segmentation-from-natural-language	0.132	0.350	0.474	0.348	0.236	0.133	0.033	0.000
actor-and-action-video-segmentation-from-a	0.198	0.421	0.536	0.475	0.347	0.211	0.08	0.002
end-to-end-referring-video-object	0.461	0.64	0.72	0.754	0.712	0.638	0.485	0.169
referring-segmentation-in-images-and-videos	-	0.432	0.618	0.487	0.431	0.358	0.231	0.052
tracking-by-natural-language-specification	0.163	0.354	0.515	0.387	0.290	0.175	0.066	0.001
polar-relative-positional-encoding-for-video	0.388	0.529	0.661	0.634	0.579	0.483	0.322	0.083
soc-semantic-assisted-object-cluster-for	0.504	0.669	0.747	0.79	0.756	0.687	0.535	0.195
spectrum-guided-multi-granularity-referring	0.585	0.720	0.799	0.843	0.822	0.767	0.617	0.259
modeling-motion-with-multi-modal-features-for	0.419	0.558	0.673	0.645	0.597	0.523	0.375	0.13
hierarchical-interaction-network-for-video	-	0.497	0.672	0.578	0.534	0.456	0.311	0.093
hierarchical-interaction-network-for-video	-	0.529	0.679	0.611	0.559	0.486	0.342	0.12