AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Human Activity Recognition using RGB-DVS Cameras: A Multi-modal Heat Conduction Model and A Benchmark Dataset

Shiao Wang, Xiao Wang, Bo Jiang, Lin Zhu, Guoqi Li, Yaowei Wang, Yonghong Tian, Jin Tang

IJCV 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 5 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
replace Vision Mamba with multi-modal heat conduction modelVision Mamba · HARDVS 2.0top-1 accuracy: 51.8 -> 53.2Improved
add modality-specific continuous frequency value embeddings (ablation)vHeat · HARDVS 2.0top-1 accuracy: 52.3 -> 52.8Improved
add policy routing based fusion (ablation)vHeat · HARDVS 2.0top-1 accuracy: 52.3 -> 52.7Improved
combine MSC and PRF (ablation)vHeat · HARDVS 2.0top-1 accuracy: 52.3 -> 53.2Improved
add event streams to RGB frames (ablation)RGB-only model · HARDVS 2.0top-1 accuracy: 49.2 -> 53.2Improved
add RGB frames to event streams (ablation)event-only model · HARDVS 2.0top-1 accuracy: 51.2 -> 53.2Improved
event-only input versus RGB-only input (ablation)single-modality model · HARDVS 2.0top-1 accuracy: 49.2 -> 51.2Improved
use adaptive routing selection instead of simple addition (ablation)fusion · HARDVS 2.0top-1 accuracy: 52.3 -> 53.2Improved
use adaptive routing instead of random selection among three fusion methods (ablation)fusion · HARDVS 2.0top-1 accuracy: 52.6 -> 53.2Improved
use concatenation instead of simple addition (ablation)fusion · HARDVS 2.0top-1 accuracy: 52.3 -> 52.3No clear effect
raise input resolution from 224x224 to 256x256 (ablation)multi-modal HCO · HARDVS 2.0top-1 accuracyHurt
use 8 input frames rather than 4 or 12 (ablation)multi-modal HCO · HARDVS 2.0top-1 accuracyImproved

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