TrajTok introduces an end‑to‑end video tokenizer that replaces traditional patchification with a lightweight, trajectory‑based tokenization process. It performs implicit clustering over space‑time pixels to generate object trajectories in a single forward pass, dynamically adjusting token granularity to semantic complexity while remaining independent of video duration. The resulting TrajViT2 model outperforms existing methods on classification and retrieval benchmarks, and TrajTok can also serve as a probing head (TrajAdapter) or alignment connector (TrajVLM) for vision‑language tasks, notably improving long‑video reasoning.
By Chenhao Zheng, Jieyu Zhang, Jianing Zhang, Weikai Huang, Ashutosh Kumar, Quan Kong, Oncel Tuzel, Chun-Liang Li, Ranjay Krishna
arXiv:2403. 07711v5 Announce Type: replace-cross Abstract: Given the remarkable achievements in image generation through diffusion models, the research community has shown increasing interest in extending these models to video generation.
By Yuta Oshima, Shohei Taniguchi, Masahiro Suzuki, Yutaka Matsuo
The paper introduces MaLoW, a streaming memory framework that internalizes long‑term video history into evolving lightweight parameter updates using a recurrent HyperNetwork and LoRA weights. MaLoW keeps current observations as input while carrying historical context forward without re‑visiting the full video stream. The authors also present MaLoW‑Instruct, a large streaming video dataset, and show that MaLoW outperforms prior memory methods on several benchmarks and improves action success in a vision‑language‑action setting.
By Zhuoming Liu, Jinhong Lin, Lin Zhang, Yiwu Zhong, Yin Li
The paper introduces Visual Query Segmentation (VQS), a new task that segments all pixel-level occurrences of a queried object in untrimmed videos. It presents VQS-4K, a large benchmark with 4,111 videos, 1.3 million frames, and 222 object categories, each paired with a visual query and annotated masklets. The authors also propose VQ‑SAM, an extension of SAM 2 that uses target‑specific and background cues to improve VQS performance, achieving state‑of‑the‑art results on VQS‑4K.
By Bing Fan, Minghao Li, Hanzhi Zhang, Shaohua Dong, Naga Prudhvi Mareedu, Xiaoqiong Liu, Weishi Shi, Yunhe Feng, Yan Huang, Heng Fan
LeVJEPA is a video encoder that eliminates the need for architectural asymmetries, exponential-moving-average target encoders, stop-gradients, and capacity-limited predictors used in prior self‑supervised methods. It trains a single encoder with an invariance loss over global and local views, regularized by SIGReg to prevent collapse, and achieves strong performance with far less pretraining compute. The approach also allows block‑causal attention, making temporal ordering a property of the encoder itself, and matches or surpasses state‑of‑the‑art baselines on both appearance‑centric and motion‑centric benchmarks.
By Lukas Kuhn, Lucas Maes, Giuseppe Serra, Quentin Le Lidec, Yann LeCun, Randall Balestriero, Florian Buettner
The paper introduces PreSTP, a training‑free method for speeding up few‑step autoregressive video diffusion models by pruning redundant tokens. It identifies two redundancy patterns—cross‑frame similarity from static content and cross‑step convergence during denoising—and uses early clean estimates from the model’s own trajectory to build a token‑wise redundancy mask. PreSTP achieves significant speedups (up to 3.20× for 5‑second videos and 1.96× for 30‑second videos) while maintaining or improving fidelity compared to existing caching baselines.
By Jia Li, Xurui Peng, Xing Wang, Hayden Kwok-Hay So
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.
By Quang-Trung Truong, Duc Thanh Nguyen, Binh-Son Hua, Sai-Kit Yeung
arXiv:2504. 01407v3 Announce Type: replace-cross Abstract: Long video understanding poses a fundamental challenge for large video-language models (LVLMs) due to the overwhelming number of frames and the risk of losing essential context through naive downsampling.
By Yuan Zhang, Junwen Pan, Rui Zhang, Xin Wan, Qizhe Zhang, Ming Lu, Qi She, Shanghang Zhang
The paper introduces Intrinsic Temporal Adaptation (ITA) for Partially Relevant Video Retrieval (PRVR), a task that seeks untrimmed videos containing moments relevant to a text query. ITA employs a Backbone-Internal Temporal Adaptation that lets the final visual transformer layers attend to neighboring frames, creating temporally aware embeddings while keeping CLIP frozen. Additionally, an Affinity-Weighted Gradient Propagation technique softly aggregates top‑k frames based on text‑frame affinities to better handle the weakly supervised nature of PRVR, leading to state‑of‑the‑art performance and more accurate frame‑level evidence retrieval.
By Hyun Seok Seong, Woojin Jun, SuBeen Lee, Jae-Pil Heo
arXiv:2606.06158v2 Announce Type: replace
Abstract: Adaptive video tokenisation seeks to dynamically allocate token budgets based on the underlying visual complexity of a sequence. Current continuous...
By Kevin Dave, Sai Aditya Patkuri, Chhaya Kumar Das, Gouranga Bala, Rajeshkumar SA, R. Venkatesh Babu
Ring Forcing is an autoregressive video diffusion framework that enhances long‑term memory by enforcing retrieval from distant history through a ring‑structured training strategy. It introduces a compression and timestep composition method to extend effective historical span to minutes, and a sparse RoPE mechanism for scalable memory adaptation. Experiments show that Ring Forcing outperforms state‑of‑the‑art models in minutes‑long coherence and object permanence.
By Bowen Xue, Brandon Y. Feng, Chenguo Lin, Yuchen Lin, Yujia Zeng, Lvmin Zhang, Maneesh Agrawala, Honglei Yan, Panwang Pan
arXiv:2607. 24794v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) demonstrate superior generalization in fundamental video tasks, restricted context windows limit their long video understanding.
By Linghao Meng, Qiankun Li, Junyuan Mao, Pujin Liao, Zhicheng He, Enbo Zhang, Kun Wang, Yang Liu, Huazhu Fu, Yueming Jin