74 accepted papers
We contend that embodied learning is fundamentally a lifecycle problem rather than a single-stage optimization. Systems that optimize only one link (data collection, simulation, learning, or deployment) rarely sustain improvement or generalize beyond narrow settings. We introduce Arcadia, a closed-l
Generalist Virtual Agents (GVAs) powered by Multimodal Large Language Models (MLLMs) exhibit impressive capabilities. However, their long-term learning is hampered by a core limitation: a failure to evolve beyond existing trajectories. This stems from memory systems that treat experiences as isolate
The rapid advancement of AI-driven video generation has transformed content creation, while simultaneously increasing the risk of misinformation through localized manipulations in long-form videos. Existing video forensic methods predominantly operate on short, independent clips, and thus fail to ca…
Large Vision-Language Models have achieved unprecedented success in zero-shot recognition by aligning visual features with broad semantic concepts. However, this semantic abstraction creates a critical vulnerability in open-world deployment: the "Hubris of Semantics", where models force-fit unknown …
Textured 3D morphing seeks to generate smooth and plausible transitions between two 3D assets, preserving both structural coherence and fine-grained appearance. This ability is crucial not only for advancing 3D generation research but also for practical applications in animation, editing, and digita…
Compared with individual agents, large language model based multi-agent systems have demonstrated great capabilities across a wide range of tasks, including code generation, mathematical reasoning, and planning, etc. Despite their impressive performance, the effectiveness and robustness of these sys…
Accurately modeling complex temporal and topological dependencies and depth information is critical for monocular 3D human pose estimation, yet existing Mamba-based approaches struggle to fulfill these demands, suffering from internal state update confusion induced by forced sequence flattening and …
Text-guided texture editing aims to modify object appearance while preserving the underlying geometric structure. However, our empirical analysis reveals that even SOTA editing models frequently struggle to maintain structural consistency during texture editing, despite the intended changes being pu…
Video-Language Models (VLMs) have demonstrated impressive multi-modal reasoning capabilities across diverse computer vision applications. However, these VLMs are task-specific and assume that both video and language inputs are complete. However, real-world VLM applications might face challenges due
In real-world multimodal applications, systems usually need to comprehend arbitrarily combined and interleaved multimodal inputs from users, while also generating outputs in any interleaved multimedia form. This capability defines the goal of any-to-any interleaved multimodal learning under a unifie
Diffusion models have demonstrated powerful capability as a versatilist for dense vision tasks, yet the generalization ability to unseen domains remains rarely explored. This paper presents HarDiff, an efficient frequency learning scheme, so as to advance generalizable paradigms for diffusion based…
Due to the critical issues of privacy and partial occlusion, license plate information is not always available in vehicle recognition systems. Consequently, researchers have increasingly turned towards vehicle re-identification (reID) techniques to bridge the gap between cross-view camera systems. D
The rapid development of Multimodal Large Language Models (MLLMs) poses increasing demands on the diversity and complexity of multimodal datasets. Yet manual annotation pipelines can no longer keep pace. Existing augmentation methods often follow fixed rules and lack verifiable control over sample d…
Domain generalization aims to learn a representation from the source domain, which can be generalized to arbitrary unseen target domains. A fundamental challenge for visual domain generalization is the domain gap caused by the dramatic style variation whereas the image content is stable. The realm…
Recently, state space models (SSM), particularly Mamba, have attracted significant attention from scholars due to their ability to effectively balance computational efficiency and performance. However, most existing visual Mamba methods flatten images into 1D sequences using predefined scan orders,…
Image restoration is a fundamental task in computer vision and machine learning, which learns a mapping between the clear images and the degraded images under various conditions (e.g., blur, low-light, haze). Yet, most existing image restoration methods are highly restricted by the requirement of de…
Computed Tomography (CT) enables detailed cross-sectional imaging but continues to face challenges in balancing reconstruction quality and computational efficiency. While deep learning-based methods have significantly improved image quality and noise reduction, they typically require large-scale tra…
Recent advances in reinforcement learning (RL) methods such as Grouped Relative Policy Optimization (GRPO) have strengthened the reasoning capabilities of Large Vision-Language Models (LVLMs). However, due to the inherent entanglement between visual and textual modalities, applying GRPO to LVLMs oft…
Audio-Visual Semantic Segmentation (AVSS) has gained significant attention in the multi-modal domain, aiming to segment video objects that produce specific sounds in the corresponding audio. Despite notable progress, existing methods still struggle to handle new classes not included in the original…
In this paper, we introduce the Generalized Video Moment Retrieval (GVMR) framework, which extends traditional Video Moment Retrieval (VMR) to handle a wider range of query types. Unlike conventional VMR systems, which are often limited to simple, single-target queries, GVMR accommodates both non-ta…
Fine-grained domain generalization (FGDG) aims to learn a fine-grained representation that can be well generalized to unseen target domains when only trained on the source domain data. Compared with generic domain generalization, FGDG is particularly challenging in that the fine-grained category can…
The advent of Multimodal Large Language Models (MLLMs) has expanded AI capabilities to visual modalities, yet existing evaluation benchmarks remain limited to single-video understanding, overlooking the critical need for multi-video understanding in real-world scenarios (e.g., sports analytics and a…
Diffusion models have emerged as a powerful paradigm for generative sequential recommendation, which typically generate next items to recommend guided by user interaction histories with a multi-step denoising process. However, the multi-step process relies on discrete approximations, introducing dis…
Spiking Neural Networks (SNNs) have shown competitive performance to Artificial Neural Networks (ANNs) in various vision tasks, while offering superior energy efficiency. However, existing SNN-based Transformers primarily focus on single-image tasks, emphasizing spatial features while not effectivel…
This paper introduces **VimoRAG**, a novel video-based retrieval-augmented motion generation framework for motion large language models (LLMs). As motion LLMs face severe out-of-domain/out-of-vocabulary issues due to limited annotated data, **VimoRAG** leverages large-scale in-the-wild video databa…
As multimodal large language models (MLLMs) advance, MLLM-based virtual agents have demonstrated remarkable performance. However, existing benchmarks face significant limitations, including uncontrollable task complexity, extensive manual annotation, and a lack of multidimensional evaluation. In res…
We investigate composed image retrieval with text feedback. Users gradually look for the target of interest by moving from coarse to fine-grained feedback. However, existing methods merely focus on the latter, i.e., fine-grained search, by harnessing positive and negative pairs during training. Thi…
Panoptic Scene Graph Generation (PSG) involves the detection of objects and the prediction of their corresponding relationships (predicates). However, the presence of biased predicate annotations poses a significant challenge for PSG models, as it hinders their ability to establish a clear decision…
Text-to-video (T2V) synthesis has gained increasing attention in the community in which the recently emerged diffusion models (DMs) have promisingly shown stronger performance than the past approaches. While existing state-of-the-art DMs are competent to achieve high-resolution video generation they…
Recent advancements in Multimodal Large Language Models (MLLMs) have been utilizing Visual Prompt Generators (VPGs) to convert visual features into tokens that LLMs can recognize. This is achieved by training the VPGs on millions of image-caption pairs, where the VPG-generated tokens of images are f…
The emerging vision foundation model (VFM) has inherited the ability to generalize to unseen images. Nevertheless, the key challenge of domain-generalized semantic segmentation (DGSS) lies in the domain gap attributed to the cross-domain styles, i.e., the variance of urban landscape and environment…
Domain generalized medical image segmentation requires models to learn from multiple source domains and generalize well to arbitrary unseen target domain. Such a task is both technically challenging and clinically practical, due to the domain shift problem (i.e., images are collected from different…
The Diffusion Probabilistic Model (DPM) has recently gained popularity in the field of computer vision, thanks to its image generation applications, such as Imagen, Latent Diffusion Models, and Stable Diffusion, which have demonstrated impressive capabilities and sparked much discussion within the c…
Video sentence grounding locates a specific moment in a video based on a text query. Existing methods focus on single temporal resolution, ignoring multi-scale temporal consistency. We introduce MRTNet, a multi-resolution grounding network with four key components: a feature encoder, a Multi-Resolut…
The development of large language models (LLMs) has greatly advanced the field of multimodal understanding, leading to the emergence of large multimodal models (LMMs). In order to enhance visual comprehension, recent studies have equipped LMMs with region-level understanding capabilities by represen…
While recently Multimodal Large Language Models (MM-LLMs) have made exciting strides, they mostly fall prey to the limitation of only input-side multimodal understanding, without the ability to produce content in multiple modalities. As we humans always perceive the world and communicate with people…
Panoptic Scene Graph Generation (PSG) parses objects and predicts their relationships (predicate) to connect human language and visual scenes. However, different language preferences of annotators and semantic overlaps between predicates lead to biased predicate annotations in the dataset, i.e. diff…
Disease grading is a crucial task in medical image analysis. Due to the continuous progression of diseases, i.e., the variability within the same level and the similarity between adjacent stages, accurate grading is highly challenging. Furthermore, in real-world scenarios, models trained on limited…
Different from the context-independent (CI) concepts such as human, car, and airplane, context-dependent (CD) concepts require higher visual understanding ability, such as camouflaged object and medical lesion. Despite the rapid advance of many CD understanding tasks in respective branches, the isol…
"Navigating drones through natural language commands remains challenging due to the dearth of accessible multi-modal datasets and the stringent precision requirements for aligning visual and textual data. To address this pressing need, we introduce GeoText-1652, a new natural language-guided geoloca…
The reasoning capabilities of LLM (Large Language Model) are widely acknowledged in recent research, inspiring studies on tool learning and autonomous agents. LLM serves as the ``brain'' of the agent, orchestrating multiple tools for collaborative multi-step task solving. Unlike methods invoking too…
Thanks to the rapid progress in RGB & thermal imaging, also known as multispectral imaging, the task of multispectral video semantic segmentation, or MVSS in short, has recently drawn significant attentions. Noticeably, it offers new opportunities in improving segmentation performance under unfavora…
Existing research of video understanding still struggles to achieve in-depth comprehension and reasoning in complex videos, primarily due to the under-exploration of two key bottlenecks: fine-grained spatial-temporal perceptive understanding and cognitive-level video scene comprehension. This paper…
Deductive reasoning is a crucial cognitive ability of humanity, allowing us to derive valid conclusions from premises and observations. However, existing works mainly focus on language-based premises and generally neglect deductive reasoning from visual observations. In this work, we introduce rule…
Accurately estimating the 3D pose and shape is an essential step towards understanding animal behavior, and can potentially benefit many downstream applications, such as wildlife conservation. However, research in this area is held back by the lack of a comprehensive and diverse dataset with high-qu…
Unpaired cross-lingual image captioning has long suffered from irrelevancy and disfluency issues, due to the inconsistencies of the semantic scene and syntax attributes during transfer. In this work, we propose to address the above problems by incorporating the scene graph (SG) structures and the sy…
Salient object detection (SOD) aims to identify standout elements in a scene, with recent advancements primarily focused on integrating depth data (RGB-D) or temporal data from videos to enhance SOD in complex scenes. However, the unison of two types of crucial information remains largely underexplo…
Short video platforms have become an important channel for news sharing, but also a new breeding ground for fake news. To mitigate this problem, research of fake news video detection has recently received a lot of attention. Existing works face two roadblocks: the scarcity of comprehensive and large…
Visual spatial description (VSD) aims to generate texts that describe the spatial relations of the given objects within images. Existing VSD work merely models the 2D geometrical vision features, thus inevitably falling prey to the problem of skewed spatial understanding of target objects. In this w…
Prompt tuning, a recently emerging paradigm, enables the powerful vision-language pre-training models to adapt to downstream tasks in a parameter- and data- efficient way, by learning the "soft prompts" to condition frozen pre-training models. Though effective, it is particularly problematic in the…
Robust and reliable semantic segmentation in complex scenes is crucial for many real-life applications such as autonomous safe driving and nighttime rescue. In most approaches, it is typical to make use of RGB images as input. They however work well only in preferred weather conditions; when facing…
The prevalence of short video platforms has spawned a lot of fake news videos, which have stronger propagation ability than textual fake news. Thus, automatically detecting fake news videos has been an important countermeasure in practice. Previous works commonly verify each news video individually…
Since developing a new multimodal LLM (MLLM) by pre-training on tremendous image-text pairs from scratch can be exceedingly resource-consuming, connecting an existing LLM with a comparatively lightweight visual prompt generator (VPG) becomes a feasible paradigm. However, further tuning the VPG compo…
Existing video-audio understanding models are trained and evaluated in an intra-domain setting, facing performance degeneration in real-world applications where multiple domains and distribution shifts naturally exist. The key to video-audio domain generalization (VADG) lies in alleviating spurious…
Scene Graph Generation (SGG) aims to extract <subject, predicate, object> relationships in images for vision understanding. Although recent works have made steady progress on SGG, they still suffer long-tail distribution that tail-predicates are more costly to train and hard to distinguish due to a…
Spatio-temporal video grounding aims to localize the aligned visual tube corresponding to a language query. Existing techniques achieve such alignment by exploiting dense boundary and bounding box annotations, which can be prohibitively expensive. To bridge the gap, we investigate the weakly-supervi…
Generally, humans are more skilled at perceiving differences between high-quality (HQ) and low-quality (LQ) images than directly judging the quality of a single LQ image. This situation also applies to image quality assessment (IQA). Although recent no-reference (NR-IQA) methods have made great prog…
Weakly-supervised temporal action localization aims to localize actions in untrimmed videos with only video-level labels. Most existing methods address this problem with a "localization-by-classification" pipeline that localizes action regions based on snippet-wise classification sequences. Snippet-…
"Scene graph generation (SGG) is designed to extract (subject, predicate, object) triplets in images. Recent works have made a steady progress on SGG, and provide useful tools for high-level vision and language understanding. However, due to the data distribution problems including long-tail distrib…
Automated generation of 3D human motions from text is a challenging problem. The generated motions are expected to be sufficiently diverse to explore the text-grounded motion space, and more importantly, accurately depicting the content in prescribed text descriptions. Here we tackle this problem wi…
Video Question Answering (VideoQA) is the task of answering questions about a video. At its core is understanding the alignments between visual scenes in video and linguistic semantics in question to yield the answer. In leading VideoQA models, the typical learning objective, empirical risk minimiza…
Vision-language pre-training (VLP) has shown impressive performance on a wide range of cross-modal tasks, where VLP models without reliance on object detectors are becoming the mainstream due to their superior computation efficiency and competitive performance. However, the removal of object detecto…
Growing interests in RGB-D salient object detection (RGB-D SOD) have been witnessed in recent years, owing partly to the popularity of depth sensors and the rapid progress of deep learning techniques. Unfortunately, existing RGB-D SOD methods typically demand large quantity of training images being…
Grounded Situation Recognition (GSR), i.e., recognizing the salient activity (or verb) category in an image (e.g.,buying) and detecting all corresponding semantic roles (e.g.,agent and goods), is an essential step towards “human-like” event understanding. Since each verb is associated with a specifi…
This survey aims to sort out the recent advances in video question answering (VideoQA) and point towards future directions. We firstly categorize the datasets into 1) normal VideoQA, multi-modal VideoQA and knowledge-based VideoQA, according to the modalities invoked in the question-answer pairs, or…
Video question answering requires the models to understand and reason about both the complex video and language data to correctly derive the answers. Existing efforts have been focused on designing sophisticated cross-modal interactions to fuse the information from two modalities, while encoding the…
We aim to address the problem of Natural Language Video Localization (NLVL) — localizing the video segment corresponding to a natural language description in a long and untrimmed video. State-of-the-art NLVL methods are almost in one-stage fashion, which can be typically grouped into two categories:…
Complex backgrounds and similar appearances between objects and their surroundings are generally recognized as challenging scenarios in Salient Object Detection (SOD). This naturally leads to the incorporation of depth information in addition to the conventional RGB image as input, known as RGB-D SO…
The ability to capture inter-frame dynamics has been critical to the development of video salient object detection (VSOD). While many works have achieved great success in this field, a deeper insight into its dynamic nature should be developed. In this work, we aim to answer the following questions:…
Training saliency detection models with weak supervisions, e.g., image-level tags or captions, is appealing as it removes the costly demand of per-pixel annotations. Despite the rapid progress of RGB-D saliency detection in fully-supervised setting, it however remains an unexplored territory when on…
In medical image analysis, it is typical to collect multiple annotations, each from a different clinical expert or rater, in the expectation that possible diagnostic errors could be mitigated. Meanwhile, from the computer vision practitioner viewpoint, it has been a common practice to adopt the grou…
Benefiting from the spatial cues embedded in depth images, recent progress on RGB-D saliency detection shows impressive ability on some challenge scenarios. However, there are still two limitations. One hand is that the pooling and upsampling operations in FCNs might cause blur object boundaries. On…
In this work, we propose a novel depth-induced multi-scale recurrent attention network for saliency detection. It achieves dramatic performance especially in complex scenarios. There are three main contributions of our network that are experimentally demonstrated to have significant practical merits…
Vocal impairment is a common symptom for the vast majority of Parkinson's disease (PD) subjects. And it needs long term rehabilitation through personalized one-to-one periodic rehabilitation meetings with clinical speech experts. The significant challenge is that there are not enough experts to deli…