AI Paper Atlas

Research map / Benchmarks / MSRVTT-QA (zero-shot)

MSRVTT-QA (zero-shot) leaderboard

12 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on MSRVTT-QA (zero-shot). Best accuracy: 67.5 (Elysium, ECCV 2024).

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.

MSRVTT-QA (zero-shot) · accuracy

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

#accuracy ↑MethodPaperTopic
167.5ElysiumElysium: Exploring Object-level Perception in Videos through Semantic Integration Using MLLMs
ECCV 2024 · Table 3
Video-language understanding
263.2ST-LLM
Vicuna-7B
ST-LLM: Large Language Models Are Effective Temporal Learners
ECCV 2024 · Table 3
Video-language understanding
362.1CAT
LLaMA2-7B
CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios
ECCV 2024 · Table 1
Visual question answering
459.8LongVLM
Vicuna-7B-v1.1 (LLaVA-7B-v1.1)
LongVLM: Efficient Long Video Understanding via Large Language Models
ECCV 2024 · Table 2
Video-language understanding
557.7PiTe
Vicuna-13B
PiTe: Pixel-Temporal Alignment for Large Video-Language Model
ECCV 2024 · Table 2
Video-language understanding
657.7LLaMA-VID
Vicuna-7B
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models
ECCV 2024 · text
Video-language understanding
723.6mPLUG-Owl2
LLaMA-2-7B
mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration
CVPR 2024 · Table 4
Cross-modal learning
822.1ProViQ (3-shot)
gpt-3.5-turbo
Video Question Answering with Procedural Programs
ECCV 2024 · Table 1
Video-language understanding
919.2BLIPBLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
ICML 2022 · Table: Video question answerin
CLIP and zero-shot
1016.7FrozenBiLM
DeBERTa-V2-XLarge
Zero-Shot Video Question Answering via Frozen Bidirectional Language Models
NeurIPS 2022 · Table 7
Visual question answering
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.