Papers with Code · CC BY-SA 4.0

Kinetics

아카이브 평가 20건 · 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
TC-CLIP	Top-1 Accuracy 78.1 Top-5 Accuracy 95.7	Leveraging Temporal Contextualization for Video Action Recognition 2024-04-15	코드 1 · 코드 2
IMP-MoE-L	Top-1 Accuracy 76.8	Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception 2023-05-10	연결 없음
OST	Top-1 Accuracy 75.1 Top-5 Accuracy 94.6	OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition 2023-11-30	코드 1
MAXI	Top-1 Accuracy 71.6	MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge 2023-03-15	코드 1
OTI（ViT-L/14）	Top-1 Accuracy 70.6	Orthogonal Temporal Interpolation for Zero-Shot Video Recognition 2023-08-14	코드 1
VideoCoCa	Top-1 Accuracy 70.1 Top-5 Accuracy 88.9	VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners 2022-12-09	연결 없음
Text4Vis	Top-1 Accuracy 68.9 Top-5 Accuracy 90.3	Revisiting Classifier: Transferring Vision-Language Models for Video Recognition 2022-07-04	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
BIKE	Top-1 Accuracy 68.5 Top-5 Accuracy 91.1	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
X-CLIP	Top-1 Accuracy 65.2 Top-5 Accuracy 86.1	Expanding Language-Image Pretrained Models for General Video Recognition 2022-08-04	코드 1 · 코드 2
LanguageBind	Top-1 Accuracy 64.1 Top-5 Accuracy 85.7	LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment 2023-10-03	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6
LoCATe-GAT	Top-1 Accuracy 58.7	LoCATe-GAT: Modeling Multi-Scale Local Context and Action Relationships for Zero-Shot Action Recognition 2024-11-27	코드 1
JigsawNet	Top-1 Accuracy 45.9 Top-5 Accuracy 78.8	Rethinking Zero-shot Action Recognition: Learning from Latent Atomic Actions 2022-03-28	코드 1
ER-ZSAR (ST+Obj)	Top-1 Accuracy 42.1 Top-5 Accuracy 73.1	Elaborative Rehearsal for Zero-shot Action Recognition 2021-08-05	코드 1
ER-ZSAR (ST)	Top-1 Accuracy 37.1 Top-5 Accuracy 69.3	Elaborative Rehearsal for Zero-shot Action Recognition 2021-08-05	코드 1
DEVISE	Top-1 Accuracy 23.8 Top-5 Accuracy 51.0	DeViSE: A Deep Visual-Semantic Embedding Model 2013-12-01	연결 없음
DEM	Top-1 Accuracy 23.6 Top-5 Accuracy 49.5	Learning a Deep Embedding Model for Zero-Shot Learning 2016-11-15	코드 1 · 코드 2 · 코드 3 · 코드 4
ALE	Top-1 Accuracy 23.4 Top-5 Accuracy 50.3	Label-Embedding for Image Classification 2015-03-30	코드 1 · 코드 2
ESZSL	Top-1 Accuracy 22.9 Top-5 Accuracy 48.3	An embarrassingly simple approach to zero-shot learning 2015-07-06	코드 1
GCN	Top-1 Accuracy 22.3 Top-5 Accuracy 49.7	All About Knowledge Graphs for Actions 2020-08-28	연결 없음
SJE(Word Embedding)	Top-1 Accuracy 22.3 Top-5 Accuracy 48.2	Evaluation of Output Embeddings for Fine-Grained Image Classification 2014-09-30	코드 1 · 코드 2