中文
相关论文

相关论文: PREGEN: Uncovering Latent Thoughts in Composed Vid…

200 篇论文

Composed Video Retrieval (CoVR) facilitates video retrieval by combining visual and textual queries. However, existing CoVR frameworks typically fuse multimodal inputs in a single stage, achieving only marginal gains over initial baseline.…

计算机视觉与模式识别 · 计算机科学 2026-01-26 Yuqian Zheng , Mariana-Iuliana Georgescu

Composed video retrieval (CoVR) is a challenging problem in computer vision which has recently highlighted the integration of modification text with visual queries for more sophisticated video search in large databases. Existing works…

计算机视觉与模式识别 · 计算机科学 2024-03-26 Omkar Thawakar , Muzammal Naseer , Rao Muhammad Anwer , Salman Khan , Michael Felsberg , Mubarak Shah , Fahad Shahbaz Khan

Recent advances in Vision-Language Models (VLMs) have enabled unified understanding across text and images, yet equipping these models with robust image generation capabilities remains challenging. Existing approaches often rely on…

计算机视觉与模式识别 · 计算机科学 2025-10-09 Xiangyi Chen , Théophane Vallaeys , Maha Elbayad , John Nguyen , Jakob Verbeek

Composed Video Retrieval (CoVR) aims to find a target video given a reference video and a textual modification. Prior work assumes the modification text fully specifies the visual changes, overlooking after-effects and implicit consequences…

Composed video retrieval is a challenging task that strives to retrieve a target video based on a query video and a textual description detailing specific modifications. Standard retrieval frameworks typically struggle to handle the…

计算机视觉与模式识别 · 计算机科学 2025-08-20 Omkar Thawakar , Dmitry Demidov , Ritesh Thawkar , Rao Muhammad Anwer , Mubarak Shah , Fahad Shahbaz Khan , Salman Khan

Perceptual video compression leverages generative priors to reconstruct realistic textures and motions at low bitrates. However, existing perceptual codecs often lack native support for variable bitrate and progressive delivery, and their…

计算机视觉与模式识别 · 计算机科学 2026-03-19 Daowen Li , Ruixiao Dong , Ying Chen , Kai Li , Ding Ding , Li Li

Understanding and reasoning over long videos pose significant challenges for large video language models (LVLMs) due to the difficulty in processing intensive video tokens beyond context window and retaining long-term sequential…

计算机视觉与模式识别 · 计算机科学 2025-10-17 Xiaoqian Shen , Wenxuan Zhang , Jun Chen , Mohamed Elhoseiny

Composed Video Retrieval (CoVR) aims to retrieve a target video from a large gallery using a reference video and a textual query specifying visual modifications. However, existing benchmarks consider only visual changes, ignoring videos…

计算机视觉与模式识别 · 计算机科学 2026-02-02 Gyuwon Han , Young Kyun Jang , Chanho Eom

Video retrieval is a challenging research topic bridging the vision and language areas and has attracted broad attention in recent years. Previous works have been devoted to representing videos by directly encoding from frame-level…

计算机视觉与模式识别 · 计算机科学 2020-06-17 Zerun Feng , Zhimin Zeng , Caili Guo , Zheng Li

Vision-Language Models (VLMs) have enabled substantial progress in video understanding by leveraging cross-modal reasoning capabilities. However, their effectiveness is limited by the restricted context window and the high computational…

计算机视觉与模式识别 · 计算机科学 2025-08-05 Zeyu Xu , Junkang Zhang , Qiang Wang , Yi Liu

In this paper, we introduce $\text{EVL}_{\text{Gen}}$, a streamlined framework designed for the pre-training of visually conditioned language generation models with high computational demands, utilizing frozen pre-trained large language…

计算机视觉与模式识别 · 计算机科学 2024-02-22 Yiren Jian , Tingkai Liu , Yunzhe Tao , Chunhui Zhang , Soroush Vosoughi , Hongxia Yang

Video Language Models (VideoLMs) enable AI systems to understand temporal dynamics in videos. To fit within the maximum context window constraint, current methods use keyframe sampling which often misses both macro-level events and…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Sayan Deb Sarkar , Rémi Pautrat , Ondrej Miksik , Marc Pollefeys , Iro Armeni , Mahdi Rad , Mihai Dusmanu

Partially Relevant Video Retrieval (PRVR) aims to retrieve untrimmed videos based on text queries that describe only partial events. Existing methods suffer from incomplete global contextual perception, struggling with query ambiguity and…

计算机视觉与模式识别 · 计算机科学 2026-04-07 Jun Li , Xuhang Lou , Jinpeng Wang , Yuting Wang , Yaowei Wang , Shu-Tao Xia , Bin Chen

Streaming video understanding with large vision-language models (VLMs) requires a compact memory that can support future reasoning over an ever-growing visual history. A common solution is to compress the key-value (KV) cache, but existing…

计算机视觉与模式识别 · 计算机科学 2026-05-15 Ailar Mahdizadeh , Puria Azadi , Muchen Li , Xiangteng He , Leonid Sigal

Partially Relevant Video Retrieval (PRVR) aims to retrieve the target video that is partially relevant to the text query. The primary challenge in PRVR arises from the semantic asymmetry between textual and visual modalities, as videos…

计算机视觉与模式识别 · 计算机科学 2025-12-01 Junlong Ren , Gangjian Zhang , Yu Hu , Jian Shu , Hui Xiong , Hao Wang

The rapid progress of large language models (LLMs) has laid the foundation for multimodal models. However, visual language models (VLMs) still face heavy computational costs when extended from images to videos due to high frame rates and…

计算机视觉与模式识别 · 计算机科学 2026-02-10 Peiran Wu , Zhuorui Yu , Yunze Liu , Chi-Hao Wu , Enmin Zhou , Junxiao Shen

Driving video generation has achieved much progress in controllability, video resolution, and length, but fails to support fine-grained object-level controllability for diverse driving videos, while preserving the spatiotemporal…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Li-Heng Chen , Ke Cheng , Yahui Liu , Lei Shi , Shi-Sheng Huang , Hongbo Fu

Visual Document Retrieval (VDR), which aims to retrieve relevant pages within vast corpora of visually-rich documents, is of significance in current multimodal retrieval applications. The state-of-the-art multi-vector paradigm excels in…

计算与语言 · 计算机科学 2026-04-21 Yibo Yan , Mingdong Ou , Yi Cao , Xin Zou , Jiahao Huo , Shuliang Liu , James Kwok , Xuming Hu

Vision-language models (VLMs) have recently emerged as a promising paradigm for video anomaly detection (VAD) due to their strong visual reasoning ability and natural language-based explainability. In this paper, we aim to address a key…

计算机视觉与模式识别 · 计算机科学 2026-05-15 Mitchell Piehl , Muchao Ye

Retrieval-Augmented Generation (RAG) is a powerful strategy for improving the factual accuracy of models by retrieving external knowledge relevant to queries and incorporating it into the generation process. However, existing approaches…

计算机视觉与模式识别 · 计算机科学 2025-05-30 Soyeong Jeong , Kangsan Kim , Jinheon Baek , Sung Ju Hwang
‹ 上一页 1 2 3 10 下一页 ›