arXiv Computer Vision October 1, 2026 By Quang-Trung Truong, Duc Thanh Nguyen, Binh-Son Hua, Sai-Kit Yeung

DiDA: Video Object Segmentation with Distillation Learning of Deformable Attention

Read the original on arXiv Computer Vision →

DiDA introduces a lightweight video object segmentation framework that leverages Distillation Learning of Deformable Attention. The method uses deformable attention to adapt key and value positions across frames, enabling object representations that are responsive to spatial and temporal changes. Experiments on DAVIS and YouTube‑VOS benchmarks show state‑of‑the‑art performance and efficient memory usage.

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.

arXiv Computer Vision

Sep 22

RefAM: Attention Magnets for Zero-Shot Referral Segmentation

arXiv:2509.22650v3 Announce Type: replace Abstract: Most existing approaches to referring segmentation achieve strong performance only through fine-tuning or by composing multiple pre-trained models,...

By Anna Kukleva, Enis Simsar, Alessio Tonioni, Muhammad Ferjad Naeem, Federico Tombari, Jan Eric Lenssen, Bernt Schiele

llms diffusion computer-vision fine-tuning multimodal benchmarks

arXiv Computer Vision

2d ago

LVMT: Video Mask Transformer for Long-term Video Segmentation

arXiv:2609.34895v2 Announce Type: replace Abstract: Existing online video segmentation methods struggle to track objects in long, complex videos with long-term occlusions. We hypothesize that this li...

By Narges Norouzi, Niccol\`{o} Cavagnero, Idil Esen Zulfikar, Bastian Leibe, Gijs Dubbelman, Daan de Geus

llms computer-vision benchmarks

arXiv AI

Jul 14

On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes

arXiv:2410. 19553v2 Announce Type: replace-cross Abstract: This paper explores the impact of occlusions in video action detection.

By Rajat Modi, Vibhav Vineet, Yogesh Singh Rawat

llms efficiency benchmarks

Hugging Face Trending Papers

Jul 8

`Attention-Guided Cross-Temporal Clustering for Self-Supervised Video Object Segmentation

Video object segmentation (VOS) is a fundamental task in video understanding, requiring accurate delineation and consistent tracking of objects across frames. While supervised methods achieve strong performance, they rely on densely annotated datasets that are costly to obtain and have limited domain coverage.

llms computer-vision safety

arXiv AI

Jun 12

HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers

arXiv:2606. 13289v1 Announce Type: cross Abstract: Holistic visual tokenizers are fundamental to unified multimodal models (UMMs) as they map diverse visual inputs into a unified representation space.

By Guozhen Zhang, Xuerui Qiu, Yutao Cui, Tianhui Song, Changlin Li, Junzhe Li, Tao Huang, Xiao Zhang, Yang Li, Jianbing Wu, Miles Yang, Zhao Zhong, Liefeng Bo, Limin Wang

llms rag diffusion computer-vision nlp multimodal

arXiv Computer Vision

1d ago

FOMO: Forget the Concept, Don't Miss Out on the Scene in Selective Video Unlearning

FOMO is a training‑based selective video unlearning method that prioritizes preserving the original scene while removing targeted concepts. It localizes concept‑related representations for modification and employs a preservation mechanism that maintains non‑target scene information without auxiliary data. The approach extends to motion unlearning, enabling removal of concepts defined by temporal behavior, and achieves a strong balance between concept removal and scene preservation.

By {\L}ukasz Rudnik, Agnieszka Polowczyk, Alicja Polowczyk, Przemys{\l}aw Spurek

One email a morning, machine-written

Related stories

RefAM: Attention Magnets for Zero-Shot Referral Segmentation

LVMT: Video Mask Transformer for Long-term Video Segmentation

On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes

`Attention-Guided Cross-Temporal Clustering for Self-Supervised Video Object Segmentation

HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers

FOMO: Forget the Concept, Don't Miss Out on the Scene in Selective Video Unlearning