AI Paper Atlas

Research map / Video / Video-language understanding

Go Beyond Earth: Understanding Human Actions and Scenes in Microgravity Environments

Di Wen, Lei Qi, Kunyu Peng, Kailun Yang, Fei Teng, Ao Luo, Jia Fu, Yufan Chen, Ruiping Liu, Yitian Shi, M. Saquib Sarfraz, Rainer Stiefelhagen

ICLR 2026 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 3 citations (OpenAlex)

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 changedWhereMeasuredEffect
evaluate AVA-tuned model on microgravity (MicroG-4M) instead of terrestrial JHMDBSlowFast R101 32x2 · zero-shot, AVA fine-tunedmAP: 47.50 -> 23.81Hurt
evaluate AVA-tuned model on microgravity (MicroG-4M) instead of terrestrial JHMDBSlow R50 8x8 · zero-shot, AVA fine-tunedmAP: 34.24 -> 16.24Hurt
add non-local modules to CNN backboneI3D R50 8x8 · MicroG-4M HAR testmAP: 46.41 -> 47.12Improved
add non-local modules to CNN backboneC2D R50 8x8 · MicroG-4M HAR testmAP: 29.51 -> 44.64Improved
use transformer models (MViT) instead of CNNsMViTv1/MViTv2 · MicroG-4M HAR testmAP: 12.86 / 15.14 vs 47.12 (I3D NLN)Hurt
use longer temporal window (Slow 4x16 vs 8x8)Slow R50 · MicroG-4M HAR validationmAP: 40.32 -> 42.97Improved
use longer temporal window (SlowFast 4x16 vs 8x8)SlowFast R50 · MicroG-4M HAR validationmAP: 38.76 -> 37.10Hurt
use dense frame sampling (90 frames) for captioningInternVideo · MicroG-4M captioningCIDEr: 0.30 -> 0.77 (vs LLaVA-NeXT 8 frames)Improved
use more input frames within the 3s window for VQAGemini 1.5 Pro · MicroG-4M VQAS-VQA: 43.15 (16 frames) vs 44.75 (Gemini 2.5 Pro, 3 frames)No clear effect
use closed-source instead of open-source video-language models for captioningGemini 1.5 Pro · MicroG-4M captioningCIDEr: 0.77 -> 3.52 (vs InternVideo)Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy