Papers with Code · CC BY-SA 4.0

Kinetics-400

아카이브 평가 205건 · 마지막 적재/변경 2026-10-30

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
OmniVec2	Acc@1 93.6	OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning 2024-01-01	연결 없음
FTP-UniFormerV2-L/14	Acc@1 93.4	Enhancing Video Transformers for Action Understanding with VLM-aided Training 2024-03-24	연결 없음
InternVideo2-6B	Acc@1 92.1	InternVideo2: Scaling Foundation Models for Multimodal Video Understanding 2024-03-22	코드 1 · 코드 2
InternVideo2-1B	Acc@1 91.6	InternVideo2: Scaling Foundation Models for Multimodal Video Understanding 2024-03-22	코드 1 · 코드 2
InternVideo	Acc@1 91.1	InternVideo: General Video Foundation Models via Generative and Discriminative Learning 2022-12-06	코드 1 · 코드 2
OmniVec	Acc@1 91.1	OmniVec: Learning robust representations with cross modal sharing 2023-11-07	연결 없음
TubeViT-H (ImageNet-1k)	Acc@1 90.9 Acc@5 98.9 FLOPs (G) x views 176400x4x3 Parameters (M) 632	Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning 2022-12-06	코드 1
Unmasked Teacher (ViT-L)	Acc@1 90.6 Acc@5 98.7 FLOPs (G) x views 1434×3×4 Parameters (M) 304	Unmasked Teacher: Towards Training-Efficient Video Foundation Models 2023-03-28	코드 1
UMT-L (ViT-L/16)	Acc@1 90.6 Acc@5 98.7	Unmasked Teacher: Towards Training-Efficient Video Foundation Models 2023-03-28	코드 1
TubeVit-L (ImageNet-1k)	Acc@1 90.2 Acc@5 98.6 FLOPs (G) x views 95300x4x3 Parameters (M) 307	Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning 2022-12-06	코드 1
UniFormerV2-L (ViT-L, 336)	Acc@1 90.0 Acc@5 98.4 FLOPs (G) x views 75300x3x2 Parameters (M) 354	UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer 2022-09-22	코드 1 · 코드 2
VideoMAE V2-g (64x266x266)	Acc@1 90.0 Acc@5 98.4	VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking 2023-03-29	코드 1
FluxViT-B	Acc@1 90.0 FLOPs (G) x views 440x3x4 Parameters (M) 97	Make Your Training Flexible: Towards Deployment-Efficient Video Models 2025-03-18	코드 1
MTV-H (WTS 60M)	Acc@1 89.9 Acc@5 98.3 FLOPs (G) x views 735700x4x3	Multiview Transformers for Video Recognition 2022-01-12	코드 1
TAdaFormer-L/14	Acc@1 89.9	Temporally-Adaptive Models for Efficient Video Understanding 2023-08-10	코드 1
EVA	Acc@1 89.7	EVA: Exploring the Limits of Masked Visual Representation Learning at Scale 2022-11-14	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6
AM/12 ViT-B Dinov2	Acc@1 89.6	AM Flow: Adapters for Temporal Processing in Action Recognition 2024-11-04	연결 없음
ATM	Acc@1 89.4 Acc@5 98.3	What Can Simple Arithmetic Operations Do for Temporal Modeling? 2023-07-18	코드 1 · 코드 2
DejaVid	Acc@1 89.1 Acc@5 98.2	DejaVid: Encoder-Agnostic Learned Temporal Matching for Video Classification 2025-01-01	코드 1
CoCa (finetuned)	Acc@1 88.9	CoCa: Contrastive Captioners are Image-Text Foundation Models 2022-05-04	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6
BIKE (CLIP ViT-L/14)	Acc@1 88.7 Acc@5 98.4	Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models 2022-12-31	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
ILA (ViT-L/14)	Acc@1 88.7 Acc@5 97.8	Implicit Temporal Modeling with Learnable Alignment for Video Recognition 2023-04-20	코드 1
Side4Video (EVA, ViT-E/14)	Acc@1 88.6 Acc@5 98.2	Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer Learning 2023-11-27	코드 1 · 코드 2
TubeVit-B (ImageNet-1k)	Acc@1 88.6 Acc@5 97.6 FLOPs (G) x views 8700x3x4 Parameters (M) 86	Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning 2022-12-06	코드 1
VideoMAE V2-g	Acc@1 88.5 Acc@5 98.1	VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking 2023-03-29	코드 1
ONE-PEACE	Acc@1 88.1 Acc@5 97.8	ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities 2023-05-18	코드 1 · 코드 2
FluxViT-S	Acc@1 88.0 FLOPs (G) x views 154x3x4 Parameters (M) 24	Make Your Training Flexible: Towards Deployment-Efficient Video Models 2025-03-18	코드 1
CoCa (frozen)	Acc@1 88.0	CoCa: Contrastive Captioners are Image-Text Foundation Models 2022-05-04	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6
ViT-22B	Acc@1 88.0	Scaling Vision Transformers to 22 Billion Parameters 2023-02-10	코드 1
Text4Vis (CLIP ViT-L/14)	Acc@1 87.8 Acc@5 97.6	Revisiting Classifier: Transferring Vision-Language Models for Video Recognition 2022-07-04	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5