AI Paper Atlas

Research map / Video / Action recognition

Otter: Mitigating Background Distractions of Wide-Angle Few-Shot Action Recognition with Enhanced RWKV

Wenbo Huang, Jinghui Zhang, Zhenghao Chen, Guang Li, Lei Zhang, Yang Cao, Fang Dong, Takahiro Ogawa, Miki Haseyama

AAAI 2026 · Video › Action recognition · approach: Disentangled action recognition · 2 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
add CSM (compound segmentation module) (ablation)Otter · SSv2 5-way 1-shotaccuracy (%): 54.6 -> 61.3Improved
add TRM (temporal reconstruction module) (ablation)Otter · SSv2 5-way 1-shotaccuracy (%): 54.6 -> 59.5Improved
add TRM on top of CSM (ablation)Otter · SSv2 5-way 1-shotaccuracy (%): 61.3 -> 64.7Improved
add CSM on top of TRM (ablation)Otter · Kinetics 5-way 1-shotaccuracy (%): 87.8 -> 90.5Improved
use patch size 56 instead of 224 (ablation)Otter · SSv2 5-way 1-shotaccuracy (%): 62.7 -> 64.7Improved
use patch size 56 instead of 28 (ablation)Otter · SSv2 5-way 1-shotaccuracy (%): 64.1 -> 64.7Improved
use multi-scale patches {28,56} instead of single p=56 (ablation)Otter · SSv2 5-way 1-shotaccuracy (%): 64.7 -> 64.2Hurt
add reversed scanning to ordered scanning in TRM (ablation)Otter · SSv2 5-way 1-shotaccuracy (%): 63.2 -> 64.7Improved
add ordered scanning to reversed scanning in TRM (ablation)Otter · SSv2 5-way 1-shotaccuracy (%): 60.6 -> 64.7Improved
use Otter instead of Manta on a wide-angle datasetFew-shot action recognition · VideoBadminton (VB to VB, 1-shot)accuracy (%): 64.1 -> 71.2Improved
use Otter instead of SOAP/Manta on UCF101 5-shotResNet-50 backbone · UCF101 5-way 5-shotaccuracy (%): 99.3 -> 99.2No clear effect
increase field of view level (outpainting and distortion) for Otter vs baselinesOtter · VideoBadminton 1-shot FoV levels 0-4accuracy (%): 71.2 -> 69.8 (Otter, Lv.0 to Lv.4)Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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