Research map / Video / Video-language understanding
EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answering
Yanjun Li, Yuqian Fu, Tianwen Qian, Qi'Ao Xu, Silong Dai, Danda Pani Paudel, Luc Van Gool, Xiaoling Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| move from in-domain EgoSchema to cross-domain EgoCross on aligned QA types | Qwen2.5-VL · EgoSchema vs EgoCross (CloseQA) | accuracy (%): 73.58 -> 43.14 | Hurt |
| egocentric-specialized training (EgoGPT, EgoVLPv2) versus general-purpose MLLMs | MLLMs on EgoCross · EgoCross overall (CloseQA) | accuracy (%): EgoGPT 30.66, EgoVLPv2 27.10 vs Qwen2.5-VL-7B 44.82 | Hurt |
| add prompt learning (ablation) | Qwen2.5-VL-7B · EgoCross pilot (CloseQA) | accuracy (%): 37.80 -> 43.76 | Improved |
| add supervised fine-tuning (ablation) | Qwen2.5-VL-7B · EgoCross pilot (CloseQA) | accuracy (%): avg 37.80 -> 43.47; Industry 35.71 -> 52.86; Surgery 37.35 -> 37.35; Animal 43.40 -> 43.40 | Mixed |
| add reinforcement learning (ablation) | Qwen2.5-VL-7B · EgoCross pilot (CloseQA) | accuracy (%): 37.80 -> 60.12 | Improved |
| serve with vLLM acceleration | Qwen2.5-VL-7B · EgoCross CloseQA | accuracy (%): 44.82 -> 37.80 | Hurt |
| use open-ended OpenQA instead of multiple-choice CloseQA | MLLMs · EgoCross overall | accuracy (%): Gemini 2.5 Pro 52.95 -> 34.40; GPT-4.1 52.63 -> 26.65 | Hurt |
Closest papers by meaning
- Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric Videos (CVPR 2025 · similarity 0.92)
- MMEgo: Towards Building Egocentric Multimodal LLMs for Video QA (ICLR 2025 · similarity 0.91)
- EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering (CVPR 2025 · similarity 0.91)
- Grounded Question-Answering in Long Egocentric Videos (CVPR 2024 · similarity 0.91)
- Grounded Multi-Hop VideoQA in Long-Form Egocentric Videos (AAAI 2025 · similarity 0.90)
- LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding (NeurIPS 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
