English
Related papers

Related papers: Interaction-Consistent Object Removal via MLLM-Bas…

200 papers

Vision benefits from grouping pixels into objects and understanding their spatial relationships, both laterally and in depth. We capture this with a scene representation comprising an occlusion-ordered stack of "object layers," each…

Computer Vision and Pattern Recognition · Computer Science 2025-08-13 Aneel Damaraju , Dean Hazineh , Todd Zickler

Despite significant advancements, current large language models (LLMs) and vision-language models (LVLMs) continue to struggle with complex, multi-step, cross-modal common sense reasoning tasks, often exhibiting a lack of "deliberative…

Computation and Language · Computer Science 2025-08-06 Wenjie Luo , Ruocheng Li , Shanshan Zhu , Julian Perry

Recent advances in reinforcement learning (RL) for large language model (LLM) fine-tuning show promise in addressing multi-objective tasks but still face significant challenges, including competing objective balancing, low training…

Computation and Language · Computer Science 2025-07-10 Lingxiao Kong , Cong Yang , Susanne Neufang , Oya Deniz Beyan , Zeyd Boukhers

Object-oriented reinforcement learning (OORL) is a promising way to improve the sample efficiency and generalization ability over standard RL. Recent works that try to solve OORL tasks without additional feature engineering mainly focus on…

Machine Learning · Computer Science 2022-10-17 Qi Yi , Rui Zhang , Shaohui Peng , Jiaming Guo , Xing Hu , Zidong Du , Xishan Zhang , Qi Guo , Yunji Chen

The generation of factually incorrect objects, commonly known as object hallucination, remains a persistent challenge in Large Vision-Language Models (LVLMs). Current approaches to address this issue - ranging from expensive data-driven…

Artificial Intelligence · Computer Science 2026-05-26 Yuanzhi Xu , Qian Gao , Jun Fan , Guohui Ding , Zhenyu Yang , Sixue Lin , Yuteng Xiao

Humans commonly identify 3D object affordance through observed interactions in images or videos, and once formed, such knowledge can be generically generalized to novel objects. Inspired by this principle, we advocate for a novel framework…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Lei Yao , Yong Chen , Yuejiao Su , Yi Wang , Moyun Liu , Lap-Pui Chau

Visual reasoning in multimodal large language models (MLLMs) has primarily been studied in static, fully observable settings, limiting their effectiveness in real-world environments where information is often incomplete due to occlusion or…

Computer Vision and Pattern Recognition · Computer Science 2025-10-27 Weijie Zhou , Xuantang Xiong , Yi Peng , Manli Tao , Chaoyang Zhao , Honghui Dong , Ming Tang , Jinqiao Wang

Composed Image Retrieval (CIR) is the task of retrieving a target image from a gallery using a composed query consisting of a reference image and a modification text. Among various CIR approaches, training-free zero-shot methods based on…

Computer Vision and Pattern Recognition · Computer Science 2025-07-18 Jeong-Woo Park , Seong-Whan Lee

Incremental object detection (IOD) aims to sequentially learn new classes, while maintaining the capability to locate and identify old ones. As the training data arrives with annotations only with new classes, IOD suffers from catastrophic…

Computer Vision and Pattern Recognition · Computer Science 2024-08-28 Jichuan Zhang , Wei Li , Shuang Cheng , Ya-Li Li , Shengjin Wang

Composed image retrieval which combines a reference image and a text modifier to identify the desired target image is a challenging task, and requires the model to comprehend both vision and language modalities and their interactions.…

Computer Vision and Pattern Recognition · Computer Science 2023-10-03 Shu Zhao , Huijuan Xu

Large Multimodal Models (LMMs) have achieved remarkable progress in generating photorealistic and prompt-aligned images, but they often produce outputs that contradict verifiable knowledge, especially when prompts involve fine-grained…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Yang Tian , Fan Liu , Jingyuan Zhang , Wei Bi , Yupeng Hu , Liqiang Nie

In Large Visual Language Models (LVLMs), the efficacy of In-Context Learning (ICL) remains limited by challenges in cross-modal interactions and representation disparities. To overcome these challenges, we introduce a novel Visual…

Computer Vision and Pattern Recognition · Computer Science 2024-02-20 Yucheng Zhou , Xiang Li , Qianning Wang , Jianbing Shen

Image-text matching (ITM) is a fundamental problem in computer vision. The key issue lies in jointly learning the visual and textual representation to estimate their similarity accurately. Most existing methods focus on feature enhancement…

Computer Vision and Pattern Recognition · Computer Science 2024-06-28 Xuri Ge , Fuhai Chen , Songpei Xu , Fuxiang Tao , Jie Wang , Joemon M. Jose

Recent advances in Multi-modal Large Language Models (MLLMs) have showcased remarkable capabilities in vision-language understanding. However, enabling robust video spatial reasoning-the ability to comprehend object locations, orientations,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Haoran Tang , Meng Cao , Ruyang Liu , Xiaoxi Liang , Linglong Li , Ge Li , Xiaodan Liang

Removing objects from videos remains difficult in the presence of real-world imperfections such as shadows, abrupt motion, and defective masks. Existing diffusion-based video inpainting models often struggle to maintain temporal stability…

Computer Vision and Pattern Recognition · Computer Science 2026-04-23 Jiagao Hu , Yuxuan Chen , Fuhao Li , Zepeng Wang , Fei Wang , Daiguo Zhou , Jian Luan

Object Re-identification (ReID) aims to retrieve the probe object from many gallery images with the ReID model inferred based on a stationary camera-free dataset by associating and collecting the identities across all camera views. When…

Computer Vision and Pattern Recognition · Computer Science 2023-05-26 Hantao Yao , Lu Yu , Jifei Luo , Changsheng Xu

Zero-Shot Composed Image Retrieval (ZS-CIR) aims to retrieve target images by integrating information from a composed query (reference image and modification text) without training samples. Existing methods primarily combine caption models…

Computer Vision and Pattern Recognition · Computer Science 2025-03-03 Zelong Sun , Dong Jing , Zhiwu Lu

Most prior works in perceiving 3D humans from images reason human in isolation without their surroundings. However, humans are constantly interacting with the surrounding objects, thus calling for models that can reason about not only the…

Computer Vision and Pattern Recognition · Computer Science 2023-11-01 Xianghui Xie , Bharat Lal Bhatnagar , Gerard Pons-Moll

Camouflaged Object Detection (COD) stands as a significant challenge in computer vision, dedicated to identifying and segmenting objects visually highly integrated with their backgrounds. Current mainstream methods have made progress in…

Computer Vision and Pattern Recognition · Computer Science 2025-12-15 Kuan Wang , Yanjun Qin , Mengge Lu , Liejun Wang , Xiaoming Tao

Real world image super-resolution (Real-ISR) often leverages the powerful generative priors of text-to-image diffusion models by regularizing the output to lie on their learned manifold. However, existing methods often overlook the…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Junoh Kang , Donghun Ryou , Bohyung Han
‹ Prev 1 3 4 5 6 7 10 Next ›