AI Paper Atlas

Research map / Benchmarks / TGIF-QA Action

TGIF-QA Action leaderboard

12 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on TGIF-QA Action. Best accuracy: 79.7 (SiaSamRea, NeurIPS 2021).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

TGIF-QA Action · accuracy

12 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
179.7SiaSamRea
ClipBERT
Learning from Inside: Self-driven Siamese Sampling and Reasoning for Video Question Answering
NeurIPS 2021 · Table 5
Video-language understanding
279.3HQGA + KPI
HQGA
Knowledge Proxy Intervention for Deconfounded Video Question Answering
ICCV 2023 · Table 1
Video-language understanding
378.1CMCIRCross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering
TPAMI 2023 · Table 5
Visual question answering
477.8HAIRHAIR: Hierarchical Visual-Semantic Relational Reasoning for Video Question Answering
ICCV 2021 · Table 1
Visual question answering
576.9HQGAVideo as Conditional Graph Hierarchy for Multi-Granular Question Answering
AAAI 2022 · Table 2
Visual question answering
675.9Bridge to AnswerBridge To Answer: Structure-Aware Graph Interaction Network for Video Question Answering
CVPR 2021 · Table: TGIF-QA performance com
Knowledge and temporal graphs
775.9QueST
ResNet-152 features
Divide and Conquer: Question-Guided Spatio-Temporal Contextual Attention for Video Question Answering
AAAI 2020 · Table 2
Video-language understanding
875.4HGAReasoning with Heterogeneous Graph Alignment for Video Question Answering
AAAI 2020 · Table 1
Visual question answering
975.2HCRN
GloVe+BiLSTM
Hierarchical Conditional Relation Networks for Multimodal Video Question Answering
IJCV 2021 · Table 1
Video-language understanding
1075.1Full 2-level HCRNHierarchical Conditional Relation Networks for Video Question Answering
CVPR 2020 · Ablation table
Video-language understanding
2 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.