The paper introduces a neural video compression technique that improves temporal context quality by combining deformable temporal alignment with difference‑aware spatial selective fusion. A Context‑aware Temporal Alignment Module generates complementary temporal context, while a Difference‑aware Spatial Selective Fusion module adaptively selects reliable temporal information and suppresses misalignment. Experiments demonstrate that this approach yields better rate‑distortion performance compared to DCVC‑DC.
TCNeRV is a new implicit neural video compression method that models temporal context in both feature and embedding domains. Its multi‑scale temporal‑context fusion module injects gated historical features across decoder scales, while temporal embedding‑residual coding predicts and encodes only the residual of each content embedding. With about 3 million parameters, TCNeRV achieves an average PSNR of 36.08 dB on the UVG dataset, outperforming HNeRV‑Boost by 2.20 dB and reducing BD‑rate by 22.06%, 66.73%, and 29.85% relative to HM, DCVC, and HiNeRV respectively.
By Xuezhi Xiang, Yixin Zhao, Heqi Xiang, Jiayao Liu, Shanjun Zhang
In video understanding, vision-language models (VLMs) must ingest massive numbers of visual tokens, causing the computational and memory cost of the prefill stage to rise sharply. Such visual sequences are highly redundant along the spatio-temporal dimension, yet a high compression ratio is often accompanied by the loss of critical details.
arXiv:2605. 20301v2 Announce Type: replace-cross Abstract: In autonomous driving, 3D object detection is essential for accurate perception and reliable decision-making.
By Wenxuan Li, Qin Zou, Shoubing Chen, Chi Chen, Yingyi Yang, Qingxiang Meng
arXiv:2606. 13580v1 Announce Type: cross Abstract: Event-based vision has drawn increasing attention owing to its distinctive properties, including ultra-high temporal resolution and extreme dynamic range.
By Dachun Kai, Jiayao Lu, Yueyi Zhang, Xiaoyan Sun
arXiv:2603.17546v2 Announce Type: replace
Abstract: Perceptual video compression leverages generative priors to reconstruct realistic textures and motions at low bitrates. However, existing perceptua...
By Daowen Li, Ruixiao Dong, Kai Li, Ying Chen, Ding Ding, Li Li
The paper introduces Feature Interaction Network (FINE), a lightweight semantic alignment module for feature fusion networks in object detectors. FINE refines low‑level features using high‑level contextual guidance through cross‑level attention, and employs Alignment‑Aware Token Sampling to reduce attention complexity. The resulting spatial‑channel modulation map selectively enhances semantically relevant pixels while preserving sub‑pixel localization, leading to improved detection accuracy with minimal computational overhead.
By Hyungseop Lee, Jiho Lee, Woochul Kang
arXiv:2606. 00508v1 Announce Type: cross Abstract: This study introduces an intriguing phenomenon in Video LLMs: rather than merely translating frames into textual embeddings, Video LLMs establish a continuous manifold, token interface, allowing visual tokens to operate as standalone entities within the architecture.
By Jungin Park, Jiyoung Lee, Kwanghoon Sohn
arXiv:2608.22861v1 Announce Type: new
Abstract: State Space Models (SSMs) have surfaced as a promising architecture in Video Frame Interpolation (VFI), as they can capture long-range dependencies wit...
By Jaehyun Park, Nam Ik Cho
arXiv:2607. 13421v1 Announce Type: cross Abstract: Spatio-Temporal Video Grounding (STVG) aims to retrieve the visual trajectory of a specific object from a video stream as described by a natural language expression.
By Kai Chen, Ming Dai, Wenxuan Cheng, Wankou Yang
arXiv:2606. 15527v1 Announce Type: cross Abstract: Typical video object-centric learning (VOCL) approaches employ slot-based frameworks that rely on reconstruction-driven encoder-decoder architectures, where learning is mediated by two spatial maps: attention maps from the encoder and object maps from the decoder.
By WonJun Moon, Jae-Pil Heo
arXiv:2511.17681v2 Announce Type: replace
Abstract: Referring Multi-Object Tracking (RMOT) extends conventional multi-object tracking (MOT) by introducing natural language references for multi-modal...
By Weiyi Lv, Ning Zhang, Hanyang Sun, Haoran Jiang, Kai Zhao, Yixiao Gu, Jing Xiao, Dan Zeng