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.
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.
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.
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.
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.
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...
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.
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.
arXiv:2510. 09608v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage.
arXiv:2605.12006v2 Announce Type: replace Abstract: The performance of promptable video object segmentation (PVOS) models substantially degrades under input corruptions, which prevents PVOS deploymen...
The paper introduces STITCH, a training‑free method that partitions videos into semantically meaningful temporal chunks using a frozen video‑text backbone. By detecting changes in the embedding sequence of short video windows, STITCH produces reusable temporal abstractions that can be applied to multiple tasks such as event boundary detection, language‑based moment retrieval, and frame selection for vision‑language models. Experiments show that STITCH performs competitively with specialized methods while requiring no task‑specific training, especially when processing is limited to a few frames or tokens.
Tetris is a video object tracking system that uses tile-level sampling to efficiently extract high‑fidelity tracks. It partitions videos into tile‑based polyominoes, classifies relevant tiles, prunes redundant ones with an ILP under a user‑defined accuracy constraint, and packs the remaining polyominoes to minimize detector calls. On seven stationary‑video datasets, Tetris maintains less than a 5% loss in tracking accuracy while achieving up to 17.4× higher throughput than prior systems and up to 68.8× higher than a full‑frame reference pipeline.