AI Paper Atlas

Research map / Benchmarks / ActivityNet-QA

ActivityNet-QA leaderboard

70 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on ActivityNet-QA. Best accuracy: 82.99 (ISR-DPO (πθ9), AAAI 2025).

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.

ActivityNet-QA · accuracy

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

#accuracy ↑MethodPaperTopic
182.99ISR-DPO (πθ9)
LLaVA-Next-7B-based VLMM
ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO
AAAI 2025 · Table 1
Multimodal LLMs
264.8LongVILA-R1-7B
LongVILA-7B
Scaling RL to Long Videos
NeurIPS 2025 · Main results table
Video-language understanding
361.8AuroraCap-7B
Vicuna-1.5-7B
AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark
ICLR 2025 · Video QA comparison table
Video-language understanding
461.3TallVA-8B-A7B
Qwen2-7B
Task-Aware Mechanism: Hybrid MoE Vision Tower Towards Holistic Video Understanding
ICML 2026 · Table 1
Video-language understanding
561.168PIC (G+E1+E2+E3)
GPT-2
Composing Ensembles of Pre-trained Models via Iterative Consensus
ICLR 2023 · Table 2
CLIP and zero-shot
660.9NVILANVILA: Efficient Frontier Visual Language Models
CVPR 2025 · Video benchmarks table
Multimodal LLMs
760.5ReMoRa
Qwen2-7B
ReMoRa: Multimodal Large Language Model based on Refined Motion Representation for Long-Video Understanding
CVPR 2026 · Table 2
Video-language understanding
860.4LLaVA-OV-7B + ReKV
LLaVA-OV-7B
Streaming Video Question-Answering with In-context Video KV-Cache Retrieval
ICLR 2025 · Offline video question-answeri
Video-language understanding
960.3CoPE-VideoLM (Ours-7B)
LLaVA-Video-7B
CoPE-VideoLM: Leveraging Codec Primitives For Efficient Video Language Modelling
NeurIPS 2026 · Table 2
Video-language understanding
1060.3VideoOrion+
Qwen2-7B
VideoOrion: Tokenizing Object Dynamics in Videos
ICCV 2025 · Table 2
Video-language understanding
60 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.