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

Despite previous image restoration (IR) methods have often concentrated on isolated degradations, recent research has increasingly focused on addressing composite degradations involving a complex combination of multiple isolated…

Referring Expression Comprehension (REC) links language to region level visual perception. Standard benchmarks (RefCOCO, RefCOCO+, RefCOCOg) have progressed rapidly with multimodal LLMs but remain weak tests of visual reasoning and…

Referring multi-object tracking (RMOT) is a task of associating all the objects in a video that semantically match with given textual queries or referring expressions. Existing RMOT approaches decompose object grounding and tracking into…

Object detection has long been dominated by traditional coordinate regression-based models, such as YOLO, DETR, and Grounding DINO. Although recent efforts have attempted to leverage MLLMs to tackle this task, they face challenges like low…

Iterative refinement has emerged as an effective paradigm for enhancing the capabilities of large language models (LLMs) on complex tasks. However, existing approaches typically implement iterative refinement at the application or prompting…

Multimodal information retrieval (MMIR) has gained attention for its flexibility in handling text, images, or mixed queries and candidates. Recent breakthroughs in multimodal large language models (MLLMs) boost MMIR performance by…

Instance-level recognition (ILR) concerns distinguishing individual instances from one another, with person re-identification as a prominent example. Despite the impressive visual perception capabilities of modern VLMs, we find their…

The rapid advancement of Large Language Models (LLMs) and Large Vision-Language Models (LVLMs) has enhanced our ability to process and generate human language and visual information. However, these models often struggle with complex,…

Image search stands as a pivotal task in multimedia and computer vision, finding applications across diverse domains, ranging from internet search to medical diagnostics. Conventional image search systems operate by accepting textual or…

Mobile service robots can benefit from object-level understanding of their environments, including the ability to distinguish object instances and re-identify previously seen instances. Object re-identification is challenging across…

Removing objects from natural images is challenging due to difficulty of synthesizing semantically coherent content while preserving background integrity. Existing methods often rely on fine-tuning, prompt engineering, or inference-time…

The fusion of language and vision in large vision-language models (LVLMs) has revolutionized deep learning-based object detection by enhancing adaptability, contextual reasoning, and generalization beyond traditional architectures. This…

Image restoration (IR) often faces various complex and unknown degradations in real-world scenarios, such as noise, blurring, compression artifacts, and low resolution, etc. Training specific models for specific degradation may lead to poor…

In-context imitation learning enables robots to adapt to new tasks from a small number of demonstrations without additional training. However, existing approaches typically condition only on state-action trajectories and lack explicit…

Learning 3D human-object interaction relation is pivotal to embodied AI and interaction modeling. Most existing methods approach the goal by learning to predict isolated interaction elements, e.g., human contact, object affordance, and…

We address the problem of machine unlearning in neural information retrieval (IR), introducing a novel task termed Neural Machine UnRanking (NuMuR). This problem is motivated by growing demands for data privacy compliance and selective…

In recent years, Multimodal Large Language Models (MLLMs) have achieved remarkable progress on a wide range of multimodal benchmarks. Despite these advances, most existing benchmarks mainly focus on single-image or multi-image…

While existing image-guided composition methods may help insert a foreground object onto a user-specified region of a background image, achieving natural blending inside the region with the rest of the image unchanged, we observe that these…

Existing methods for reconstructing objects and humans from a monocular image suffer from severe mesh collisions and performance limitations for interacting occluding objects. This paper introduces a method to obtain a globally consistent…

Existing multi-turn image editing paradigms are often confined to isolated single-step execution. Due to a lack of context-awareness and closed-loop feedback mechanisms, they are prone to error accumulation and semantic drift during…