54 accepted papers
Facial expression recognition (FER) in the wild is severely hampered by label noise and annotation ambiguity. Existing methods, including sample selection, label ensembling, and consistency regularization, primarily rely on ordinary label supervision and offer limited control over non-target predict
3D visual grounding encompassing 3D referring expression comprehension (3DREC) and segmentation (3DRES) requires robust cross-modal representation to achieve fine-grained semantic alignment and precise geometric reasoning. However, most methods employ unimodal pre-trained encoders that transfer visu…
Medical image segmentation supports clinical workflows by precisely delineating anatomical structures and lesions. However, medical image datasets medical image datasets suffer from acquisition noise and annotation ambiguity, causing pervasive data uncertainty that substantially undermines model rob
Semantic understanding of large-scale aerial scenes represents a critical challenge in 3D computer vision, hindered by the prohibitive cost of dense annotation. This paper introduces EvoPropGS, a novel approach for the semantic segmentation of 3D Gaussian Splatting models that requires only minimal
Real-time satellite video tracking poses distinct challenges, including accommodating high spatial-temporal resolution, dynamic backgrounds, and constrained onboard computational resources. While Discriminative Correlation Filter (DCF)-based methods offer high-speed inference, they suffer from limit…
In this paper, we propose GenSplat, a novel approach for language comprehension in 3D Gaussian Splatting (3DGS). Unlike previous methods that either achieve cross-scene generalization by being bounded to a predefined vocabulary or handle free-form language by overfitting to individual scenes, GenSpl
In recent years, the rapid progress of deep learning has driven notable advancements in satellite video tracking, a critical task for applications such as environmental monitoring, disaster management, and defense. Despite these strides, existing approaches remain constrained by their inability to h
Modeling large-scale landscapes is a foundational yet time-consuming task in many 3D applications, typically requiring substantial expertise. Recently, Text-to-3D techniques have emerged as a promising, beginner-friendly prototyping approach for generating 3D content from textual input. However, ex
Multimodal Large Language Models excel at offline audio-visual understanding, but their ability to serve as mobile assistants in continuous real-world streams remains underexplored. In daily phone use, mobile assistants must track streaming audio-visual inputs and respond at the right time, yet exis…
LLMs excel at predictive tasks and complex reasoning tasks, but many high-value deployments rely on decisions under uncertainty, for example, which tool to call, which expert to consult, or how many resources to invest. While the usefulness and feasibility of Bayesian approaches remain unclear for L…
Existing studies on preference optimization (PO) have been focused on constructing pairwise preference data following simple heuristics, such as maximizing the margin between chosen and rejected responses based on human (or AI) ratings. In this work, we develop a novel PO framework that provides th
RGB-T tracking is increasingly deployed in safety-critical applications such as autonomous driving, surveillance, and rescue robotics, where tracking reliability is essential under adverse conditions. Although the fusion of RGB and thermal infrared (TIR) modalities offers improved robustness in low-
Transforming sparse, partial pixel sketches from diverse media into complete, editable vector drawings is essential yet underexplored in digital creation. Prior methods either generate from scratch or inpaint local gaps without predicting global structure, leading to coarse contours and limited deta
Despite the advancements in diffusion-based image style transfer, existing methods are commonly limited by 1) semantic gap: the style reference could miss proper content semantics, causing uncontrollable stylization; 2) reliance on extra constraints (e.g., semantic masks) restricting applicability;
Handcrafted optimizers become prohibitively inefficient for complex black-box optimization (BBO) tasks. MetaBBO addresses this challenge by meta-learning to automatically configure optimizers for low-level BBO tasks, thereby eliminating heuristic dependencies. However, existing methods typically req…
Text-driven 3D editing, enabled by advancements in 3D reconstruction techniques such as NeRF and 3D Gaussian Splatting, aims to provide intuitive scene customization. However, existing methods frequently exhibit limitations in controllability and consistency. To address these shortcomings, we propos
From image to video understanding, the capabilities of Multi-modal LLMs (MLLMs) are increasingly powerful. However, most existing video understanding benchmarks are relatively short, which makes them inadequate for effectively evaluating the long-sequence modeling capabilities of MLLMs. This highlig…
Current advanced long-context language models offer great potential for real-world software engineering applications. However, progress in this critical domain remains hampered by a fundamental limitation: the absence of a rigorous evaluation framework for long code understanding. To gap this obstac…
Domain generalization in 3D segmentation is a critical challenge in deploying models to unseen environments. Current methods mitigate the domain shift by augmenting the data distribution of point clouds. However, the model learns global geometric patterns in point clouds while ignoring the category-…
Dynamic Scene Graph Generation (DSGG) aims to comprehensively understand videos by abstracting them into visual triplets <subject, predicate, object>. Most existing methods focus on capturing temporal dependencies, but overlook crucial visual relationship dependencies between entities and predicates…
We introduce GaussianOcc, a systematic method that investigates Gaussian splatting for fully self-supervised and efficient 3D occupancy estimation in surround views. First, traditional methods for self-supervised 3D occupancy estimation still require ground truth 6D poses from sensors during trainin…
Vision-language models like CLIP have demonstrated strong zero-shot generalization, making them valuable for various downstream tasks through prompt learning. However, existing test-time prompt tuning methods, such as entropy minimization, treat both text and visual prompts as fixed learnable parame…
Visual grounding (VG) refers to detecting the specific objects in images based on linguistic expressions, and it has profound significance in the advanced interpretation of natural images. In remote sensing image interpretation, visual grounding is limited by characteristics such as the complex scen
Salient Object Ranking (SOR) aims to study human attention shifts across different objects in the scene. It is a challenging task, as it requires comprehension of the relations among the salient objects in the scene. However, existing works often overlook such relations or model them implicitly. In…
With its powerful visual-language alignment capability, CLIP performs well in zero-shot and few-shot learning tasks. However, we found in experiments that CLIP's logits suffer from serious inter-class confusion problems in downstream tasks, and the ambiguity between categories seriously affects the…
Panoptic segmentation unifies the traditional tasks of instance and semantic segmentation. It plays a crucial role in the field of remote sensing; however, it encounters challenges in recognizing small objects and in the model’s ability to generalize across complex scenes. In this paper, we introduc…
Graph Neural Networks (GNNs) have excelled in diverse applications due to their outstanding predictive performance, yet they often overlook fairness considerations, prompting numerous recent efforts to address this societal concern. However, most fair GNNs assume complete demographics by design, whi
Natural language processing for programming aims to use NLP techniques to assist programming. It is increasingly prevalent for its effectiveness in improving productivity. Distinct from natural language, a programming language is highly structured and functional. Constructing a structure-based repre…
Diffusion models trained on large-scale datasets have achieved remarkable progress in image synthesis. However due to the randomness in the diffusion process they often struggle with handling diverse low-level tasks that require details preservation. To overcome this limitation we present a new Diff…
Although deep generative models have greatly improved one-shot video-driven talking head generation, few studies address fine-grained controllable facial expression editing, which is crucial for practical applications. Existing methods rely on a fixed set of predefined discrete emotion labels or sim…
Recent research has shown significant interest in image-based glass surface detection (GSD). However, detecting glass surfaces in dynamic scenes remains largely unexplored due to the lack of a high-quality dataset and an effective video glass surface detection (VGSD) method. In this paper, we propos…
Neural Radiance Fields (NeRF) have been successfully applied in various aerial scenes yet they face challenges with sparse views due to limited supervision. The acquisition of dense aerial views is often prohibitive as unmanned aerial vehicles (UAVs) may encounter constraints in perspective range an…
Move structures have been studied in English for Specific Purposes (ESP) and English for Academic Purposes (EAP) for decades. However, there are few move annotation corpora for Research Article (RA) abstracts. In this paper, we introduce RAAMove, a comprehensive multi-domain corpus dedicated to the…
Removing shadows requires an understanding of both lighting conditions and object textures in a scene. Existing methods typically learn pixel-level color mappings between shadow and non-shadow images, in which the joint modeling of lighting and object textures is implicit and inadequate. We observe…
Social media popularity prediction of multimodal user-generated content (UGC) is a crucial task for many real-world applications. However, existing efforts are often limited by missing inter-instance correlations and UGC temporal patterns. To address these issues, we propose a novel time-aware hyper…
Pre-trained vision-language(V-L) models such as CLIP have demonstrated impressive Zero-Shot performance in many downstream tasks. Since adopting contrastive video-text pairs methods like CLIP to video tasks is limited by its high cost and scale, recent approaches focus on efficiently transferring th…
To address the challenges of long-tailed classification, researchers have proposed several approaches to reduce model bias, most of which assume that classes with few samples are weak classes. However, recent studies have shown that tail classes are not always hard to learn, and model bias has been…
Model bias triggered by long-tailed data has been widely studied. However, measure based on the number of samples cannot explicate three phenomena simultaneously: (1) Given enough data, the classification performance gain is marginal with additional samples. (2) Classification performance decays pre…
Personalized Federated Learning (FL) handles the data heterogeneous problem by tailoring local models for each distributed data owner. Previous studies first train a highly-adaptable global model and then transfer it for personalization. However, the additional training aggravates burden of resource…
Existing Referring Image Segmentation (RIS) methods typically require expensive pixel-level or box-level annotations for supervision. In this paper, we observe that the referring texts used in RIS already provide sufficient information to localize the target object. Hence, we propose a novel weakly-…
Facial expression recognition (FER) has recently attracted attention in computer vision. However, existing methods mostly focus on the explicit performance and overlook their computational resources and memory consumption. Hence, achieving promising performance while maintaining the efficiency of mo…
The inherent slow imaging speed of Magnetic Resonance Image (MRI) has spurred the development of various acceleration methods, typically through heuristically undersampling of the associated measurement domain known as k-space. Recently, deep neural networks have been applied to reconstruct undersam…
Training speaker-discriminative and robust speaker verification systems without speaker labels is still challenging and worthwhile to explore. In this study, we propose an effective self-supervised learning framework and a novel regularization strategy to facilitate self-supervised speaker represent…
Weakly supervised Video Anomaly Detection (VAD) using Multi-Instance Learning (MIL) is usually based on the fact that the anomaly score of an abnormal snippet is higher than that of a normal snippet. In the beginning of training, due to the limited accuracy of the model, it is easy to select the wro…
"Most few-shot image classification methods are trained based on tasks. Usually, tasks are built on base classes with a large number of labeled images, which consumes large effort. Unsupervised few-shot image classification methods do not need labeled images, because they require tasks to be built o…
Word-character lattice models have been proved to be effective for Chinese named entity recognition (NER), in which word boundary information is fused into character sequences for enhancing character representations. However, prior approaches have only used simple methods such as feature concatenati…
The memory consumption of most Convolutional Neural Network (CNN) architectures grows rapidly with increasing depth of the network, which is a major constraint for efficient network training on modern GPUs with limited memory, embedded systems, and mobile devices. Several studies show that the featu…
3D point cloud semantic segmentation has attracted wide attention with its extensive applications in autonomous driving, AR/VR, and robot sensing fields. However, in existing methods, each point in the segmentation results is predicted independently from each other. This property causes the non-cont…
Joint extraction of entities and their relations benefits from the close interaction between named entities and their relation information. Therefore, how to effectively model such cross-modal interactions is critical for the final performance. Previous works have used simple methods such as label-…
Sketch-based image retrieval (SBIR) has been a popular research topic in recent years. Existing works concentrate on mapping the visual information of sketches and images to a semantic space at the object level. In this paper, for the first time, we study the fine-grained scene-level SBIR problem wh…
As common cancer, breast cancer kills thousands of women every year. It’s significant to provide doctors computer-aided diagnosis (CAD) to ease their workload as well as improve detection quality. Patch-level CNNs are usually used to classify the breast tissue slice, and the CNNs classify each patch…
Stochastic multi-armed bandits form a class of online learning problems that have important applications in online recommendation systems, adaptive medical treatment, and many others. Even though potential attacks against these learning algorithms may hijack their behavior, causing catastrophic loss…
Hand-drawn sketch recognition is a fundamental problem in computer vision, widely used in sketch-based image and video retrieval, editing, and reorganization. Previous methods often assume that a complete sketch is used as input; however, hand-drawn sketches in common application scenarios are often…
Model compression is significant for the wide adoption of Recurrent Neural Networks (RNNs) in both user devices possessing limited resources and business clusters requiring quick responses to large-scale service requests. This work aims to learn structurally-sparse Long Short-Term Memory (LSTM) by r…