← Back to all news
arXiv Computer Vision By JeongRae Kim, Chaehyun Kim, Changwon Lim

SAM3Dual: A 3rd Place Solution to the MOSEv2 Track, 8th LSVOS Challenge

Read the original on arXiv Computer Vision →

SAM3Dual is a training‑free inference extension of pretrained SAM 3 that won third place in the MOSEv2 track of the 8th Large‑scale Video Object Segmentation Challenge. It separates temporal memory into short‑term and long‑term branches, fuses their responses deterministically, and modulates them with previous‑frame confidence, all while keeping SAM 3 parameters frozen. The approach achieved an official J&F score of 64.37, demonstrating competitive long‑term VOS performance without task‑specific training.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Aug 27

LongVU-TTT: Causal Test-Time Training for Visual Resampling in Long Video Understanding

LongVU‑TTT is a causal test‑time training method for long‑video multimodal large language models that inserts a convolutional resampler with fast‑weight updates between the vision encoder and the LLM. The fast weights adapt per video and contextualize frame features before compression, while a hybrid selector keeps explicit visual evidence for downstream reasoning. Experiments show that TTT‑Conv outperforms TTT‑MLP and bidirectional Mamba2 on MLVU, and beats attention‑ and fixed‑state recurrent resamplers on three benchmarks, achieving competitive results on five video‑understanding tasks after reducing 512 frames to 128 LLM frames.

By Mahmoud Ahmed, Sameh Abdulah, Olatunji Ruwase, Sam Ade Jacobs, Mathis Bode, Mohamed Elhoseiny
llmsbenchmarks
More like this →
arXiv Computer Vision
Oct 5

When Predicting Nothing Beats SAM 3: Revisiting Evaluation in Video Object Segmentation

The paper introduces FaVOS, a benchmark for Video Object Segmentation (VOS) that focuses on scenarios where target objects appear only intermittently over long videos. It demonstrates that the standard J&F metric can be gamed by empty predictions, allowing trivial models to outperform strong ones like SAM 3. To address this, the authors propose Volumetric J&F, which treats mask sequences as spatio‑temporal volumes, reducing the influence of target‑absence rewards while maintaining sensitivity to segmentation quality and temporal structure.

By Jihwan Hong, Woohyeon Park, Jaeik Kim, Jaeyoung Do
computer-visionbenchmarks
More like this →