70 accepted papers
Generating anomalies is a crucial method to enhance detection and classification performance by expanding anomalous data repository. However, existing anomaly generation methods overlook the intrinsic entanglement between diverse anomaly types and product structures, leading to semantic ambiguity. W
The human brain constructs emotional percepts not by processing facial expressions in isolation, but through a dynamic, hierarchical integration of sensory input with semantic and contextual knowledge. However, existing vision-based dynamic emotion modeling approaches often neglect emotion perceptio…
Few-shot multimodal industrial anomaly detection is a critical yet underexplored task, offering the ability to quickly adapt to complex industrial scenarios. In few-shot settings, insufficient training samples often fail to cover the diverse patterns present in test samples. This challenge can be mi
Active 3D reconstruction relies on active view selection to maximize reconstruction fidelity under limited capture budgets. However, most existing methods rely on surrogate signals—such as parameter uncertainty or geometric heuristics—which are often misaligned with the ultimate goal: the fidelity o…
Multimodal Large Language Models (MLLMs) have shown great promise but require substantial computational resources during inference. Attackers can exploit this by inducing excessive output, leading to resource exhaustion and service degradation. Prior energy-latency attacks aim to increase generation…
Recent subject-driven image customization excels in fidelity, yet fine-grained instance-level spatial control remains an elusive challenge, hindering real-world applications. This limitation stems from two factors: a scarcity of scalable, position-annotated datasets, and the entanglement of identity
Text-guided object segmentation requires both cross-modal reasoning and pixel grounding abilities. Most recent methods treat it as a single forward pass, where the model directly predicts pixel prompts to a segmentation model, which limits verification, refocusing and refinement when initial localiz…
Legged robots offer significant potential for navigating complex industrial terrains, but their capabilities are often constrained by perception systems struggling to interpret intricate 3D geometry. Conventional 2D/2.5D representations like depth or elevation maps fail to capture complex 3D geometr…
Multimodal Large Language Models (MLLMs) have unlocked powerful cross-modal capabilities, but still significantly suffer from hallucinations. As such, accurate detection of hallucinations in MLLMs is imperative for ensuring their reliability in practical applications. To this end, guided by the prin
Multimodal visual object tracking can be divided into to several kinds of tasks (e.g. RGB and RGB+X tracking), based on the input modality. Existing methods often train separate models for each modality or rely on pretrained models to adapt to new modalities, which limits efficiency, scalability, an…
Large Language Models (LLMs) often struggle with mathematical reasoning tasks requiring precise, verifiable computation. While Reinforcement Learning (RL) from outcome-based rewards enhances text-based reasoning, understanding how agents autonomously learn to leverage external tools like code execu…
Deep neural networks are vulnerable to adversarial examples that exhibit transferability across various models. Numerous approaches are proposed to enhance the transferability of adversarial examples, including advanced optimization, data augmentation, and model modifications. However, these methods…
Anomaly detection is critical in industrial manufacturing for ensuring product quality and improving efficiency in automated processes. The scarcity of anomalous samples limits traditional detection methods, making anomaly generation essential for expanding the data repository. However, recent gener
The current advancements in Dynamic Facial Expression Recognition (DFER) methods mainly focus on better capturing the spatial and temporal features of facial expressions. However, DFER datasets contain a substantial amount of noisy samples, and few have addressed the issue of handling this noise. We…
UAV tracking can be widely applied in scenarios such as disaster rescue, environmental monitoring, and logistics transportation. However, existing UAV tracking methods predominantly emphasize speed and lack exploration in semantic awareness, which hinders the search region from extracting accurate l…
Preference alignment in diffusion models has primarily focused on benign human preferences (e.g., aesthetic). In this paper, we propose a novel perspective: framing unrestricted adversarial example generation as a problem of aligning with adversary preferences. Unlike benign alignment, adversarial a…
Vision-Language-Action (VLA) models have advanced general-purpose robotic manipulation by leveraging pretrained visual and linguistic representations. However, they struggle with contact-rich tasks that require fine-grained control involving force, especially under visual occlusion or dynamic uncert…
Previous works have attempted to improve tracking efficiency through lightweight architecture design or knowledge distillation from teacher models to compact student trackers. However, these solutions often sacrifice accuracy for speed to a great extent, and also have the problems of complex trainin…
Anomaly detection and localization in automated industrial manufacturing can significantly enhance production efficiency and product quality. Existing methods are capable of detecting surface defects in pre-defined or controlled imaging environments. However, accurately detecting workpiece defects i
Dynamic Facial Expression Recognition (DFER) is crucial for affective computing but often overlooks the impact of scene context. We have identified a significant issue in current DFER tasks: human annotators typically integrate emotions from various angles, including environmental cues and body lang…
Open-vocabulary Video Instance Segmentation (OpenVIS) can simultaneously detect, segment, and track arbitrary object categories in a video, without being constrained to categories seen during training. In this work, we propose InstFormer, a carefully designed framework for the OpenVIS task that achi…
Video Camouflaged Object Detection (VCOD) aims to segment objects whose appearances closely resemble their surroundings, posing a challenging and emerging task. Existing vision models often struggle in such scenarios due to the indistinguishable appearance of camouflaged objects and the insufficient…
Pre-trained vision-language models have exhibited remarkable abilities in detecting out-of-distribution (OOD) samples. However, some challenging OOD samples, which lie close to in-distribution (InD) data in image feature space, can still lead to misclassification. The emergence of foundation models…
Video segmentation is essential for advancing robotics and autonomous driving, particularly in open-world settings where continuous perception and object association across video frames are critical. While the Segment Anything Model (SAM) has excelled in static image segmentation, extending its capa
Well-designed prompts have demonstrated the potential to guide text-to-image models in generating amazing images. Although existing prompt engineering methods can provide high-level guidance, it is challenging for novice users to achieve the desired results by manually entering prompts due to a disc…
"Pre-trained diffusion models utilized for image generation encapsulate a substantial reservoir of a priori knowledge pertaining to intricate textures. Harnessing the potential of leveraging this a priori knowledge in the context of image super-resolution presents a compelling avenue. Nonetheless, p…
Data-Free Knowledge Distillation (DFKD) is a promising task to train high-performance small models to enhance actual deployment without relying on the original training data. Existing methods commonly avoid relying on private data by utilizing synthetic or sampled data. However a long-overlooked iss…
Previous visual object tracking methods employ image-feature regression models or coordinate autoregression models for bounding box prediction. Image-feature regression methods heavily depend on matching results and do not utilize positional prior, while the autoregressive approach can only be train…
In industrial quality control, detecting defects is essential. However, manual checks and machine vision encounter challenges in complex conditions, as defects vary among products made of different materials and shapes. We create FD-UAD, Unsupervised Anomaly Detection Platform Based on Defect Autono…
The Janus Problem is a common issue in SDS-based text-to-3D methods. Due to view encoding approach and 2D diffusion prior guidance, the 3D representation model tends to learn content with higher certainty from each perspective, leading to view inconsistency. In this work, we first model and analyze…
In software development, resolving the emergent issues within GitHub repositories is a complex challenge that involves not only the incorporation of new code but also the maintenance of existing code. Large Language Models (LLMs) have shown promise in code generation but face difficulties in resolvi…
Visual object tracking aims to localize the target object of each frame based on its initial appearance in the first frame. Depending on the input modility tracking tasks can be divided into RGB tracking and RGB+X (e.g. RGB+N and RGB+D) tracking. Despite the different input modalities the core aspec…
Adversarial Robustness Distillation (ARD) is a promising task to solve the issue of limited adversarial robustness of small capacity models while optimizing the expensive computational costs of Adversarial Training (AT). Despite the good robust performance, the existing ARD methods are still impract…
"Panoramic videos contain richer spatial information and have attracted tremendous amounts of attention due to their exceptional experience in some fields such as autonomous driving and virtual reality. However, existing datasets for video segmentation only focus on conventional planar images. To ad…
Establishing precise semantic correspondence across object instances in different images is a fundamental and challenging task in computer vision. In this task difficulty arises often due to three challenges: confusing regions with similar appearance inconsistent object scale and indistinguishable n…
Adversarial Robustness Distillation (ARD) is a novel method to boost the robustness of small models. Unlike general adversarial training, its robust knowledge transfer can be less easily restricted by the model capacity. However, the teacher model that provides the robustness of knowledge does not a…
This work focuses on sign language retrieval--a recently proposed task for sign language understanding. Sign language retrieval consists of two sub-tasks: text-to-sign-video (T2V) retrieval and sign-video-to-text (V2T) retrieval. Different from traditional video-text retrieval, sign language videos,…
Unrestricted adversarial attacks typically manipulate the semantic content of an image (e.g., color or texture) to create adversarial examples that are both effective and photorealistic, demonstrating their ability to deceive human perception and deep neural networks with stealth and success. Howeve…
This paper solves the problem of learning dense visual correspondences between different object instances of the same category with only sparse annotations. We decompose this pixel-level semantic matching problem into two easier ones: (i) First, local feature descriptors of source and target images…
Although Deep Neural Networks (DNNs) have demonstrated excellent performance, they are vulnerable to adversarial patches that introduce perceptible and localized perturbations to the input. Generating adversarial patches on images has received much attention, while adversarial patches on videos have…
Few-Shot Object Detection (FSOD) is designed to detect unseen objects using a few examples. Matching between query image and support instance via metric learning has been shown to be an effective FSOD method. In previous work, the quality of proposals generated by the RPN is not yet high due to the…
Detecting out-of-distribution inputs for visual recognition models has become critical in safe deep learning. This paper proposes a novel hierarchical visual category modeling scheme to separate out-of-distribution data from in-distribution data through joint representation learning and statistical…
Learning a policy with great generalization to unseen environments remains challenging but critical in visual reinforcement learning. Despite the success of augmentation combination in the supervised learning generalization, naively applying it to visual RL algorithms may damage the training efficie…
Existing video object segmentation (VOS) benchmarks focus on short-term videos which just last about 3-5 seconds and where objects are visible most of the time. These videos are poorly representative of practical applications, and the absence of long-term datasets restricts further investigation of…
Semantic correspondence have built up a new way for object recognition. However current single-object matching schema can be hard for discovering commonalities for a category and far from the real-world recognition tasks. To fill this gap, we design the multi-instance semantic correspondence task wh…
This paper introduces a new few-shot learning pipeline that casts relevance ranking for image retrieval as binary ranking relation classification. In comparison to image classification, ranking relation classification is sample efficient and domain agnostic. Besides, it provides a new perspective on…
Reference features from a template or historical frames are crucial for visual object tracking. Prior works utilize all features from a fixed template or memory for visual object tracking. However, due to the dynamic nature of videos, the required reference historical information for different searc…
This paper focuses on the two problems of the similar objects distraction and the lack of robustness for unseen object categories in semi-supervised video object segmentation task. Existing methods have achieved great results on the benchmark dataset, but these two problems still have not been compl…
This paper introduces an effective and tiny model for real-time Camouflaged Object Detection (COD) named Tiny-COD. It achieves high performance with very low costs (Parameters < 5M, FLOPs < 1.5G), which can be applied on mobile devices. Specifically, we introduce a simple but effective Adjacent Scal…
This paper presents new hierarchically cascaded transformers that can improve data efficiency through attribute surrogates learning and spectral tokens pooling. Vision transformers have recently been thought of as a promising alternative to convolutional neural networks for visual recognition. But w…
Studying the inherent symmetry of data is of great importance in machine learning. Point cloud, the most important data format for 3D environmental perception, is naturally endowed with strong radial symmetry. In this work, we exploit this radial symmetry via a divide-and-conquer strategy to boost 3…
Recently, adversarial attacks have been applied in visual object tracking to deceive deep trackers by injecting imperceptible perturbations into video frames. However, previous work only generates the video-specific perturbations, which restricts its application scenarios. In addition, existing atta…
Current benchmarks for facial expression recognition (FER) mainly focus on static images, while there are limited datasets for FER in videos. It is still ambiguous to evaluate whether performances of existing methods remain satisfactory in real-world application-oriented scenes. For example, the "Ha…
Video Object Segmentation (VOS) is a fundamental task in video recognition with many practical applications. It aims at predicting segmentation masks of multiple objects in an entire video. Recent video object segmentation(VOS) researches have achieved remarkable performance. However, as a video pro…
Named entity recognition and relation extraction are two important core subtasks of information extraction, which aim to identify named entities and extract relations between them. In recent years, span representation methods have received a lot of attention and are widely used to extract entities a…
Convolutional Neural Networks (CNNs) approaches are widely applied to histopathological image analysis due to the breakthrough performance achieved. However, it remains challenging because complex backgrounds obscure the most discriminative region. In this paper, we propose selective scale cascade a…
"Though deep neural networks (DNNs) have demonstrated excellent performance in computer vision, they are susceptible and vulnerable to carefully crafted adversarial examples which can mislead DNNs to incorrect outputs. Patch attack is one of the most threatening forms, which has the potential to thr…
In this paper, we propose a conceptually novel, efficient, and fully convolutional framework for real-time instance segmentation. Previously, most instance segmentation methods heavily rely on object detection and perform mask prediction based on bounding boxes or dense centers. In contrast, we prop…
Although vision transformers (ViTs) have achieved great success in computer vision, the heavy computational cost hampers their applications to dense prediction tasks such as semantic segmentation on mobile devices. In this paper, we present a mobile-friendly architecture named Token Pyramid Vision T…
Patch attacks, one of the most threatening forms of physical attack in adversarial examples, can lead networks to induce misclassification by modifying pixels arbitrarily in a continuous region. Certifiable patch defense can guarantee robustness that the classifier is not affected by patch attacks.…
Medical Visual Question Answering (Med-VQA) helps answer medical questions raised by patients automatically so as to relieve the shortage of experienced doctors. Cross-modal feature alignment is a major challenge of Med-VQA. Moreover, it is critical to exploit sufficient semantic features with the c…
Current state-of-the-art saliency detection models rely heavily on large datasets of accurate pixel-wise annotations, but manually labeling pixels is time-consuming and labor-intensive. There are some weakly supervised methods developed for alleviating the problem, such as image label, bounding box…
Online knowledge distillation (OKD), which simultaneously trains several peer networks to construct a powerful teacher on on-the-fly, has drawn much attention in recent years. OKD is designed to simplify the training procedure of conventional offline distillation. However, the ensemble strategy of e…
Domain adaptation for semantic segmentation enables to alleviate the need for large-scale pixel-wise annotations. Recently, self-supervised learning (SSL) with a combination of image-to-image translation shows great effectiveness in adaptive segmentation. The most common practice is to perform SSL a…
High-level features can help low-level features eliminate semantic ambiguity, which is crucial for obtaining the precise salient object. Some methods use high-level features to provide global guidance for some layers of the network. However, there remain several problems: (1) the global guidance has…
Multilingual question answering over knowledge graph (KGQA) aims to derive answers from a knowledge graph (KG) for questions in multiple languages. To be widely applicable, we focus on its zero-shot transfer setting. That is, we can only access training data in a high-resource language, while need t…
Labelling image-sentence is expensive and some unsupervised image captioning methods show promising results on caption generation. However, the generated captions are not very relevant to images due to the excessive dependence on the corpus. In order to overcome that drawback, we focus on the corres…
Nowadays, driver drowsiness and driver distraction is considered as a major risk for fatal road accidents around the world. As a result, driver monitoring identifying is emerging as an essential function of automotive safety systems. Its basic features include head pose, gaze direction, yawning and…
Vehicle re-identification (re-id) is challenging due to the small inter-class distance. The differences between similar vehicles can be extremely subtle and only captured at particular scales and semantic levels. In this paper, we propose a novel Multi-Scale Deep Feature Fusion Network (MSDeep) to c…
We propose a novel and flexible anchor mechanism named MetaAnchor for object detection frameworks. Unlike many previous detectors model anchors via a predefined manner, in MetaAnchor anchor functions could be dynamically generated from the arbitrary customized prior boxes. Taking advantage of weight…