Lap-Pui Chau

Yufei Wang, Wenhan Yang, Xinyuan Chen et al.

While super-resolution (SR) methods based on diffusion models exhibit promising results, their practical application is hindered by the substantial number of required inference steps. Recent methods utilize degraded images in the initial state, thereby shortening the Markov chain. Nevertheless, these solutions either rely on a precise formulation of the degradation process or still necessitate a relatively lengthy generation path (e.g., 15 iterations). To enhance inference speed, we propose a simple yet effective method for achieving single-step SR generation, named SinSR. Specifically, we first derive a deterministic sampling process from the most recent state-of-the-art (SOTA) method for accelerating diffusion-based SR. This allows the mapping between the input random noise and the generated high-resolution image to be obtained in a reduced and acceptable number of inference steps during training. We show that this deterministic mapping can be distilled into a student model that performs SR within only one inference step. Additionally, we propose a novel consistency-preserving loss to simultaneously leverage the ground-truth image during the distillation process, ensuring that the performance of the student model is not solely bound by the feature manifold of the teacher model, resulting in further performance improvement. Extensive experiments conducted on synthetic and real-world datasets demonstrate that the proposed method can achieve comparable or even superior performance compared to both previous SOTA methods and the teacher model, in just one sampling step, resulting in a remarkable up to x10 speedup for inference. Our code will be released at https://github.com/wyf0912/SinSR

Tianyi Liu, Kejun Wu, Yi Wang et al.

The past decade has witnessed great strides in video recovery by specialist technologies, like video inpainting, completion, and error concealment. However, they typically simulate the missing content by manual-designed error masks, thus failing to fill in the realistic video loss in video communication (e.g., telepresence, live streaming, and internet video) and multimedia forensics. To address this, we introduce the bitstream-corrupted video (BSCV) benchmark, the first benchmark dataset with more than 28,000 video clips, which can be used for bitstream-corrupted video recovery in the real world. The BSCV is a collection of 1) a proposed three-parameter corruption model for video bitstream, 2) a large-scale dataset containing rich error patterns, multiple corruption levels, and flexible dataset branches, and 3) a plug-and-play module in video recovery framework that serves as a benchmark. We evaluate state-of-the-art video inpainting methods on the BSCV dataset, demonstrating existing approaches' limitations and our framework's advantages in solving the bitstream-corrupted video recovery problem. The benchmark and dataset are released at https://github.com/LIUTIGHE/BSCV-Dataset.

Andrea Piazzoni, Jim Cherian, Justin Dauwels et al.

Even though virtual testing of Autonomous Vehicles (AVs) has been well recognized as essential for safety assessment, AV simulators are still undergoing active development. One particularly challenging question is to effectively include the Sensing and Perception (S&P) subsystem into the simulation loop. In this article, we define Perception Error Models (PEM), a virtual simulation component that can enable the analysis of the impact of perception errors on AV safety, without the need to model the sensors themselves. We propose a generalized data-driven procedure towards parametric modeling and evaluate it using Apollo, an open-source driving software, and nuScenes, a public AV dataset. Additionally, we implement PEMs in SVL, an open-source vehicle simulator. Furthermore, we demonstrate the usefulness of PEM-based virtual tests, by evaluating camera, LiDAR, and camera-LiDAR setups. Our virtual tests highlight limitations in the current evaluation metrics, and the proposed approach can help study the impact of perception errors on AV safety.

Junlong Li, Chao Hao, Lap-Pui Chau et al.

Existing agentic reinforcement learning methods for GUI grounding have limitations at two levels. At the data level, current approaches typically treat all training samples equally, although their training value to the baseline model varies with difficulty. Overlooking this can greatly reduce training efficiency or even cause collapse. At the strategy level, existing frameworks struggle to balance the trade-off between cropping larger regions for sufficient context and smaller ones for reduced redundancy, a tension inherent to tool-augmented grounding agents. In addition, overly complex decision-making is difficult for small-parameter models and significantly increases inference time. To address these issues, at the data level, we propose GUI-D, a data mining and difficulty scoring pipeline that identifies the training-worthy samples by proper testing and assigns difficulty scores to guide subsequent training weights. At the strategy level, we propose GUI-C$^2$, which employs an area-gated coarse-to-fine refinement mechanism that progressively narrows the visual field via model-internal uncertainty signals, adaptively reserving context for large targets while amplifying precision for small ones, reinforced by improvement-aware stage rewards that ensure each refinement genuinely advances grounding. Meanwhile, we simplify the decision-making process to greatly reduce additional inference time. Finally, extensive experiments show that our method achieves state-of-the-art performance. The code and data will be publicly available.

Wenyang Liu, Yi Wang, Kim-Hui Yap et al.

In this paper, we study a real-world JPEG image restoration problem with bit errors on the encrypted bitstream. The bit errors bring unpredictable color casts and block shifts on decoded image contents, which cannot be resolved by existing image restoration methods mainly relying on pre-defined degradation models in the pixel domain. To address these challenges, we propose a robust JPEG decoder, followed by a two-stage compensation and alignment framework to restore bitstream-corrupted JPEG images. Specifically, the robust JPEG decoder adopts an error-resilient mechanism to decode the corrupted JPEG bitstream. The two-stage framework is composed of the self-compensation and alignment (SCA) stage and the guided-compensation and alignment (GCA) stage. The SCA adaptively performs block-wise image color compensation and alignment based on the estimated color and block offsets via image content similarity. The GCA leverages the extracted low-resolution thumbnail from the JPEG header to guide full-resolution pixel-wise image restoration in a coarse-to-fine manner. It is achieved by a coarse-guided pix2pix network and a refine-guided bi-directional Laplacian pyramid fusion network. We conduct experiments on three benchmarks with varying degrees of bit error rates. Experimental results and ablation studies demonstrate the superiority of our proposed method. The code will be released at https://github.com/wenyang001/Two-ACIR.

Wenyang Liu, Yi Wang, Kejun Wu et al.

File fragment classification (FFC) on small chunks of memory is essential in memory forensics and Internet security. Existing methods mainly treat file fragments as 1d byte signals and utilize the captured inter-byte features for classification, while the bit information within bytes, i.e., intra-byte information, is seldom considered. This is inherently inapt for classifying variable-length coding files whose symbols are represented as the variable number of bits. Conversely, we propose Byte2Image, a novel data augmentation technique, to introduce the neglected intra-byte information into file fragments and re-treat them as 2d gray-scale images, which allows us to capture both inter-byte and intra-byte correlations simultaneously through powerful convolutional neural networks (CNNs). Specifically, to convert file fragments to 2d images, we employ a sliding byte window to expose the neglected intra-byte information and stack their n-gram features row by row. We further propose a byte sequence \& image fusion network as a classifier, which can jointly model the raw 1d byte sequence and the converted 2d image to perform FFC. Experiments on FFT-75 dataset validate that our proposed method can achieve notable accuracy improvements over state-of-the-art methods in nearly all scenarios. The code will be released at https://github.com/wenyang001/Byte2Image.

Wenbin Zou, Tianyi Li, Kejun Wu et al.

This paper reports on the NTIRE 2026 Challenge on Bitstream-Corrupted Video Restoration (BSCVR). The challenge aims to advance research on recovering visually coherent videos from corrupted bitstreams, whose decoding often produces severe spatial-temporal artifacts and content distortion. Built upon recent progress in bitstream-corrupted video recovery, the challenge provides a common benchmark for evaluating restoration methods under realistic corruption settings. We describe the dataset, evaluation protocol, and participating methods, and summarize the final results and main technical trends. The challenge highlights the difficulty of this emerging task and provides useful insights for future research on robust video restoration under practical bitstream corruption.

Yufei Wang, Yi Yu, Wenhan Yang et al.

Previous raw image-based low-light image enhancement methods predominantly relied on feed-forward neural networks to learn deterministic mappings from low-light to normally-exposed images. However, they failed to capture critical distribution information, leading to visually undesirable results. This work addresses the issue by seamlessly integrating a diffusion model with a physics-based exposure model. Different from a vanilla diffusion model that has to perform Gaussian denoising, with the injected physics-based exposure model, our restoration process can directly start from a noisy image instead of pure noise. As such, our method obtains significantly improved performance and reduced inference time compared with vanilla diffusion models. To make full use of the advantages of different intermediate steps, we further propose an adaptive residual layer that effectively screens out the side-effect in the iterative refinement when the intermediate results have been already well-exposed. The proposed framework can work with both real-paired datasets, SOTA noise models, and different backbone networks. Note that, the proposed framework is compatible with real-paired datasets, real/synthetic noise models, and different backbone networks. We evaluate the proposed method on various public benchmarks, achieving promising results with consistent improvements using different exposure models and backbones. Besides, the proposed method achieves better generalization capacity for unseen amplifying ratios and better performance than a larger feedforward neural model when few parameters are adopted.

Yufei Wang, Yi Yu, Wenhan Yang et al.

While raw images exhibit advantages over sRGB images (e.g., linearity and fine-grained quantization level), they are not widely used by common users due to the large storage requirements. Very recent works propose to compress raw images by designing the sampling masks in the raw image pixel space, leading to suboptimal image representations and redundant metadata. In this paper, we propose a novel framework to learn a compact representation in the latent space serving as the metadata in an end-to-end manner. Furthermore, we propose a novel sRGB-guided context model with improved entropy estimation strategies, which leads to better reconstruction quality, smaller size of metadata, and faster speed. We illustrate how the proposed raw image compression scheme can adaptively allocate more bits to image regions that are important from a global perspective. The experimental results show that the proposed method can achieve superior raw image reconstruction results using a smaller size of the metadata on both uncompressed sRGB images and JPEG images.

Ying Zheng, Lei Yao, Yuejiao Su et al.

Embodied learning for object-centric robotic manipulation is a rapidly developing and challenging area in embodied AI. It is crucial for advancing next-generation intelligent robots and has garnered significant interest recently. Unlike data-driven machine learning methods, embodied learning focuses on robot learning through physical interaction with the environment and perceptual feedback, making it especially suitable for robotic manipulation. In this paper, we provide a comprehensive survey of the latest advancements in this field and categorize the existing work into three main branches: 1) Embodied perceptual learning, which aims to predict object pose and affordance through various data representations; 2) Embodied policy learning, which focuses on generating optimal robotic decisions using methods such as reinforcement learning and imitation learning; 3) Embodied task-oriented learning, designed to optimize the robot's performance based on the characteristics of different tasks in object grasping and manipulation. In addition, we offer an overview and discussion of public datasets, evaluation metrics, representative applications, current challenges, and potential future research directions. A project associated with this survey has been established at https://github.com/RayYoh/OCRM_survey.

Jiawei Lian, Shaohui Mei, Xiaofei Wang et al.

It has been widely substantiated that deep neural networks (DNNs) are susceptible and vulnerable to adversarial perturbations. Existing studies mainly focus on performing attacks by corrupting targeted objects (physical attack) or images (digital attack), which is intuitively acceptable and understandable in terms of the attack's effectiveness. In contrast, our focus lies in conducting background adversarial attacks in both digital and physical domains, without causing any disruptions to the targeted objects themselves. Specifically, an effective background adversarial attack framework is proposed to attack anything, by which the attack efficacy generalizes well between diverse objects, models, and tasks. Technically, we approach the background adversarial attack as an iterative optimization problem, analogous to the process of DNN learning. Besides, we offer a theoretical demonstration of its convergence under a set of mild but sufficient conditions. To strengthen the attack efficacy and transferability, we propose a new ensemble strategy tailored for adversarial perturbations and introduce an improved smooth constraint for the seamless connection of integrated perturbations. We conduct comprehensive and rigorous experiments in both digital and physical domains across various objects, models, and tasks, demonstrating the effectiveness of attacking anything of the proposed method. The findings of this research substantiate the significant discrepancy between human and machine vision on the value of background variations, which play a far more critical role than previously recognized, necessitating a reevaluation of the robustness and reliability of DNNs. The code will be publicly available at https://github.com/JiaweiLian/Attack_Anything

Yufei Wang, Yi Yu, Wenhan Yang et al.

While raw images have distinct advantages over sRGB images, e.g., linearity and fine-grained quantization levels, they are not widely adopted by general users due to their substantial storage requirements. Very recent studies propose to compress raw images by designing sampling masks within the pixel space of the raw image. However, these approaches often leave space for pursuing more effective image representations and compact metadata. In this work, we propose a novel framework that learns a compact representation in the latent space, serving as metadata, in an end-to-end manner. Compared with lossy image compression, we analyze the intrinsic difference of the raw image reconstruction task caused by rich information from the sRGB image. Based on the analysis, a novel backbone design with asymmetric and hybrid spatial feature resolutions is proposed, which significantly improves the rate-distortion performance. Besides, we propose a novel design of the context model, which can better predict the order masks of encoding/decoding based on both the sRGB image and the masks of already processed features. Benefited from the better modeling of the correlation between order masks, the already processed information can be better utilized. Moreover, a novel sRGB-guided adaptive quantization precision strategy, which dynamically assigns varying levels of quantization precision to different regions, further enhances the representation ability of the model. Finally, based on the iterative properties of the proposed context model, we propose a novel strategy to achieve variable bit rates using a single model. This strategy allows for the continuous convergence of a wide range of bit rates. Extensive experimental results demonstrate that the proposed method can achieve better reconstruction quality with a smaller metadata size.

Yuejiao Su, Yi Wang, Lap-Pui Chau

Egocentric Interactive hand-object segmentation (EgoIHOS) requires the segmentation of hands and interacting objects in egocentric images, which is crucial for understanding human behavior in assistive systems. Previous methods typically recognize hands and interacting objects as distinct semantic categories based solely on visual features, or simply use hand predictions as auxiliary cues for object segmentation. Despite the promising progress achieved by these methods, they fail to adequately model the interactive relationships between hands and objects while ignoring the coupled physical relationships among object categories, ultimately constraining their segmentation performance. To make up for the shortcomings of existing methods, we propose a novel method called CaRe-Ego that achieves state-of-the-art performance by emphasizing the contact between hands and objects from two aspects. First, we introduce a Hand-guided Object Feature Enhancer (HOFE) to establish the hand-object interactive relationships to extract more contact-relevant and discriminative object features. Second, we design the Contact-centric Object Decoupling Strategy (CODS) to explicitly model and disentangle coupling relationships among object categories, thereby emphasizing contact-aware feature learning. Experiments on various in-domain and out-of-domain test sets show that Care-Ego significantly outperforms existing methods with robust generalization capability. Codes are publicly available at https://github.com/yuggiehk/CaRe-Ego/.

Jiawei Lian, Jianhong Pan, Lefan Wang et al.

Physical attacks against object detection have gained increasing attention due to their significant practical implications. However, conducting physical experiments is extremely time-consuming and labor-intensive. Moreover, physical dynamics and cross-domain transformation are challenging to strictly regulate in the real world, leading to unaligned evaluation and comparison, severely hindering the development of physically robust models. To accommodate these challenges, we explore utilizing realistic simulation to thoroughly and rigorously benchmark physical attacks with fairness under controlled physical dynamics and cross-domain transformation. This resolves the problem of capturing identical adversarial images that cannot be achieved in the real world. Our benchmark includes 20 physical attack methods, 48 object detectors, comprehensive physical dynamics, and evaluation metrics. We also provide end-to-end pipelines for dataset generation, detection, evaluation, and further analysis. In addition, we perform 8064 groups of evaluation based on our benchmark, which includes both overall evaluation and further detailed ablation studies for controlled physical dynamics. Through these experiments, we provide in-depth analyses of physical attack performance and physical adversarial robustness, draw valuable observations, and discuss potential directions for future research. Codebase: https://github.com/JiaweiLian/Benchmarking_Physical_Attack

Yufei Wang, Renjie Wan, Wenhan Yang et al.

A protector is placed in front of the camera lens for mobile devices to avoid damage, while the protector itself can be easily scratched accidentally, especially for plastic ones. The artifacts appear in a wide variety of patterns, making it difficult to see through them clearly. Removing image artifacts from the scratched lens protector is inherently challenging due to the occasional flare artifacts and the co-occurring interference within mixed artifacts. Though different methods have been proposed for some specific distortions, they seldom consider such inherent challenges. In our work, we consider the inherent challenges in a unified framework with two cooperative modules, which facilitate the performance boost of each other. We also collect a new dataset from the real world to facilitate training and evaluation purposes. The experimental results demonstrate that our method outperforms the baselines qualitatively and quantitatively. The code and datasets will be released after acceptance.

Shaohui Mei, Jiawei Lian, Xiaofei Wang et al.

Deep neural networks (DNNs) have found widespread applications in interpreting remote sensing (RS) imagery. However, it has been demonstrated in previous works that DNNs are vulnerable to different types of noises, particularly adversarial noises. Surprisingly, there has been a lack of comprehensive studies on the robustness of RS tasks, prompting us to undertake a thorough survey and benchmark on the robustness of image classification and object detection in RS. To our best knowledge, this study represents the first comprehensive examination of both natural robustness and adversarial robustness in RS tasks. Specifically, we have curated and made publicly available datasets that contain natural and adversarial noises. These datasets serve as valuable resources for evaluating the robustness of DNNs-based models. To provide a comprehensive assessment of model robustness, we conducted meticulous experiments with numerous different classifiers and detectors, encompassing a wide range of mainstream methods. Through rigorous evaluation, we have uncovered insightful and intriguing findings, which shed light on the relationship between adversarial noise crafting and model training, yielding a deeper understanding of the susceptibility and limitations of various models, and providing guidance for the development of more resilient and robust models

Andrea Piazzoni, Jim Cherian, Roshan Vijay et al.

In this paper, we introduce the notion of Cooperative Perception Error Models (coPEMs) towards achieving an effective and efficient integration of V2X solutions within a virtual test environment. We focus our analysis on the occlusion problem in the (onboard) perception of Autonomous Vehicles (AV), which can manifest as misdetection errors on the occluded objects. Cooperative perception (CP) solutions based on Vehicle-to-Everything (V2X) communications aim to avoid such issues by cooperatively leveraging additional points of view for the world around the AV. This approach usually requires many sensors, mainly cameras and LiDARs, to be deployed simultaneously in the environment either as part of the road infrastructure or on other traffic vehicles. However, implementing a large number of sensor models in a virtual simulation pipeline is often prohibitively computationally expensive. Therefore, in this paper, we rely on extending Perception Error Models (PEMs) to efficiently implement such cooperative perception solutions along with the errors and uncertainties associated with them. We demonstrate the approach by comparing the safety achievable by an AV challenged with a traffic scenario where occlusion is the primary cause of a potential collision.

Lei Yao, Yi Wang, Yawen Cui et al.

Query-based 3D scene instance segmentation from point clouds has attained notable performance. However, existing methods suffer from the query initialization dilemma due to the sparse nature of point clouds and rely on computationally intensive attention mechanisms in query decoders. We accordingly introduce LaSSM, prioritizing simplicity and efficiency while maintaining competitive performance. Specifically, we propose a hierarchical semantic-spatial query initializer to derive the query set from superpoints by considering both semantic cues and spatial distribution, achieving comprehensive scene coverage and accelerated convergence. We further present a coordinate-guided state space model (SSM) decoder that progressively refines queries. The novel decoder features a local aggregation scheme that restricts the model to focus on geometrically coherent regions and a spatial dual-path SSM block to capture underlying dependencies within the query set by integrating associated coordinates information. Our design enables efficient instance prediction, avoiding the incorporation of noisy information and reducing redundant computation. LaSSM ranks first place on the latest ScanNet++ V2 leaderboard, outperforming the previous best method by 2.5% mAP with only 1/3 FLOPs, demonstrating its superiority in challenging large-scale scene instance segmentation. LaSSM also achieves competitive performance on ScanNet, ScanNet200, S3DIS and ScanNet++ V1 benchmarks with less computational cost. Extensive ablation studies and qualitative results validate the effectiveness of our design. The code and weights are available at https://github.com/RayYoh/LaSSM.

Ying Zheng, Yiyi Zhang, Yi Wang et al.

Source-Free Domain Adaptation (SFDA) adapts pre-trained models to unlabeled target domains without requiring access to source data. Although state-of-the-art methods leveraging local neighborhood structures show promise for SFDA, they tend to over-rely on prediction similarity among neighbors. This over-reliance accelerates the forgetting of source knowledge and increases susceptibility to local noise overfitting. To address these issues, we introduce ProCal, a probability calibration method that dynamically calibrates neighborhood-based predictions through a dual-model collaborative prediction mechanism. ProCal integrates the source model's initial predictions with the current model's online outputs to effectively calibrate neighbor probabilities. This strategy not only mitigates the interference of local noise but also preserves the discriminative information from the source model, thereby achieving a balance between knowledge retention and domain adaptation. Furthermore, we design a joint optimization objective that combines a soft supervision loss with a diversity loss to guide the target model. Our theoretical analysis shows that ProCal converges to an equilibrium where source knowledge and target information are effectively fused, reducing both knowledge forgetting and overfitting. We validate the effectiveness of our approach through extensive experiments on 31 cross-domain tasks across four public datasets. Our code is available at: https://github.com/zhengyinghit/ProCal.

Yuejiao Su, Yi Wang, Lei Yao et al.

A fine-grained understanding of egocentric human-environment interactions is crucial for developing next-generation embodied agents. One fundamental challenge in this area involves accurately parsing hands and active objects. While transformer-based architectures have demonstrated considerable potential for such tasks, several key limitations remain unaddressed: 1) existing query initialization mechanisms rely primarily on semantic cues or learnable parameters, demonstrating limited adaptability to changing active objects across varying input scenes; 2) previous transformer-based methods utilize pixel-level semantic features to iteratively refine queries during mask generation, which may introduce interaction-irrelevant content into the final embeddings; and 3) prevailing models are susceptible to "interaction illusion", producing physically inconsistent predictions. To address these issues, we propose an end-to-end Interaction-aware Transformer (InterFormer), which integrates three key components, i.e., a Dynamic Query Generator (DQG), a Dual-context Feature Selector (DFS), and the Conditional Co-occurrence (CoCo) loss. The DQG explicitly grounds query initialization in the spatial dynamics of hand-object contact, enabling targeted generation of interaction-aware queries for hands and various active objects. The DFS fuses coarse interactive cues with semantic features, thereby suppressing interaction-irrelevant noise and emphasizing the learning of interactive relationships. The CoCo loss incorporates hand-object relationship constraints to enhance physical consistency in prediction. Our model achieves state-of-the-art performance on both the EgoHOS and the challenging out-of-distribution mini-HOI4D datasets, demonstrating its effectiveness and strong generalization ability. Code and models are publicly available at https://github.com/yuggiehk/InterFormer.

Wenbin Zou, Yawen Cui, Yi Wang et al.

State space models (SSMs) have emerged as a powerful paradigm for efficient single-image super-resolution (SR) due to their linear complexity and long-range modeling capabilities. However, existing Mamba-based methods typically rely on data-agnostic rigid scanning, which reshapes 2D images into 1D sequences over a fixed grid, inevitably disrupting spatial-semantic topology and introducing artifacts. Inspired by the \textbf{Gestalt perceptual grouping theory}, we propose \textbf{SP-MoMamba}, a superpixel-driven mixture of state space experts designed for content-aware SR. Our core idea is to transform the traditional rigid scanning into a \textbf{semantic-level interaction} by treating superpixels as fundamental units. Specifically, we introduce the \textbf{Superpixel-driven State Space Model (SP-SSM)}, which compresses semantically homogeneous regions into high-order tokens to preserve global topological consistency. To address the conflict between fixed scanning scales and diverse semantic granularities, we develop the \textbf{Multi-Scale Superpixel Mixture of State Space Experts (MSS-MoE)}. This module utilizes a dynamic routing mechanism to adaptively assign scale-specific experts, effectively capturing multi-scale textures while reducing computational redundancy. Furthermore, to prevent the loss of high-frequency details during global abstraction, we introduce a \textbf{Local Spatial Modulation Expert (LSME)} to complement the global modeling, ensuring a precise reconstruction of sharp edges and fine structures. Extensive experiments on standard benchmarks demonstrate that SP-MoMamba achieves superior reconstruction fidelity and a more favorable efficiency-performance trade-off compared to state-of-the-art efficient SR methods.

Jiawei Lian, Jianhong Pan, Lefan Wang et al.

Large Language Models (LLMs) increasingly employ alignment techniques to prevent harmful outputs. Despite these safeguards, attackers can circumvent them by crafting adversarial prompts. Predominant token-level optimization methods primarily rely on optimizing for exact affirmative templates (e.g., ``\textit{Sure, here is...}''). However, these paradigms frequently encounter bottlenecks such as suboptimal convergence, compromised prompt naturalness, and poor cross-model generalization. To address these limitations, we propose Semantic Representation Attack (SRA), a novel LLM-agnostic paradigm that fundamentally reconceptualizes adversarial objectives from exact textual targeting to malicious semantic representations. Theoretically, we establish the semantic Coherence-Convergence Relationship and derive a Cross-Model Semantic Generalization bound, proving that maintaining semantic coherence guarantees both white-box semantic convergence and black-box transferability. Technically, we operationalize this framework via the Semantic Representation Heuristic Search (SRHS) algorithm, which preserves interpretability and structural coherence of the adversarial prompts during incremental discrete token chunk expansion. Extensive evaluations demonstrate that our framework achieves a 99.71% average attack success rate across 26 open-source LLMs, with strong transferability and stealth.

Lei Yao, Yi Wang, Moyun Liu et al.

In recent years, transformer-based models have exhibited considerable potential in point cloud instance segmentation. Despite the promising performance achieved by existing methods, they encounter challenges such as instance query initialization problems and excessive reliance on stacked layers, rendering them incompatible with large-scale 3D scenes. This paper introduces a novel method, named SGIFormer, for 3D instance segmentation, which is composed of the Semantic-guided Mix Query (SMQ) initialization and the Geometric-enhanced Interleaving Transformer (GIT) decoder. Specifically, the principle of our SMQ initialization scheme is to leverage the predicted voxel-wise semantic information to implicitly generate the scene-aware query, yielding adequate scene prior and compensating for the learnable query set. Subsequently, we feed the formed overall query into our GIT decoder to alternately refine instance query and global scene features for further capturing fine-grained information and reducing complex design intricacies simultaneously. To emphasize geometric property, we consider bias estimation as an auxiliary task and progressively integrate shifted point coordinates embedding to reinforce instance localization. SGIFormer attains state-of-the-art performance on ScanNet V2, ScanNet200 datasets, and the challenging high-fidelity ScanNet++ benchmark, striking a balance between accuracy and efficiency. The code, weights, and demo videos are publicly available at https://rayyoh.github.io/sgiformer.

Huaiyuan Xu, Junliang Chen, Shiyu Meng et al.

3D occupancy perception technology aims to observe and understand dense 3D environments for autonomous vehicles. Owing to its comprehensive perception capability, this technology is emerging as a trend in autonomous driving perception systems, and is attracting significant attention from both industry and academia. Similar to traditional bird's-eye view (BEV) perception, 3D occupancy perception has the nature of multi-source input and the necessity for information fusion. However, the difference is that it captures vertical structures that are ignored by 2D BEV. In this survey, we review the most recent works on 3D occupancy perception, and provide in-depth analyses of methodologies with various input modalities. Specifically, we summarize general network pipelines, highlight information fusion techniques, and discuss effective network training. We evaluate and analyze the occupancy perception performance of the state-of-the-art on the most popular datasets. Furthermore, challenges and future research directions are discussed. We hope this paper will inspire the community and encourage more research work on 3D occupancy perception. A comprehensive list of studies in this survey is publicly available in an active repository that continuously collects the latest work: https://github.com/HuaiyuanXu/3D-Occupancy-Perception.

Mingjin Chen, Junhao Chen, Zhaoxin Fan et al.

Recent methods have made notable progress in the visual quality of hand-object interaction video synthesis. However, most approaches rely on 2D control signals that lack spatial expressiveness and limit the utilization of synthetic 3D conditional data. To address these limitations, we propose HVG-3D, a unified framework for 3D-aware hand-object interaction (HOI) video synthesis conditioned on explicit 3D representations. Specifically, we develop a diffusion-based architecture augmented with a 3D ControlNet, which encodes geometric and motion cues from 3D inputs to enable explicit 3D reasoning during video synthesis. To achieve high-quality synthesis, HVG-3D is designed with two core components: (i) a 3D-aware HOI video generation diffusion architecture that encodes geometric and motion cues from 3D inputs for explicit 3D reasoning; and (ii) a hybrid pipeline for constructing input and condition signals, enabling flexible and precise control during both training and inference. During inference, given a single real image and a 3D control signal from either simulation or real data, HVG-3D generates high-fidelity, temporally consistent videos with precise spatial and temporal control. Experiments on the TASTE-Rob dataset demonstrate that HVG-3D achieves state-of-the-art spatial fidelity, temporal coherence, and controllability, while enabling effective utilization of both real and simulated data.

Tianyi Liu, Ye Lu, Linfeng Zhang et al.

Diffusion-based video editing has emerged as an important paradigm for high-quality and flexible content generation. However, despite their generality and strong modeling capacity, Diffusion Transformers (DiT) remain computationally expensive due to the iterative denoising process, posing challenges for practical deployment. Existing video diffusion acceleration methods primarily exploit denoising timestep-level feature reuse, which mitigates the redundancy in denoising process, but overlooks the architectural redundancy within the DiT that many attention operations over spatio-temporal tokens are redundantly executed, offering little to no incremental contribution to the model output. This work introduces HetCache, a training-free diffusion acceleration framework designed to exploit the inherent heterogeneity in diffusion-based masked video-to-video (MV2V) generation and editing. Instead of uniformly reuse or randomly sampling tokens, HetCache assesses the contextual relevance and interaction strength among various types of tokens in designated computing steps. Guided by spatial priors, it divides the spatial-temporal tokens in DiT model into context and generative tokens, and selectively caches the context tokens that exhibit the strongest correlation and most representative semantics with generative ones. This strategy reduces redundant attention operations while maintaining editing consistency and fidelity. Experiments show that HetCache achieves a noticeable acceleration, including a 2.67$\times$ latency speedup and FLOPs reduction over commonly used foundation models, with negligible degradation in editing quality.

Ying Zheng, Yiyi Zhang, Yi Wang et al.

Conventional deep network training generally optimizes all samples under a largely uniform learning paradigm, without explicitly modeling the heterogeneous competition among them. Such an oversimplified treatment can lead to several well-known issues, including bias under class imbalance, insufficient learning of hard samples, and the erroneous reinforcement of noisy samples. In this work, we present \textit{Natural Selection} (NS), a novel evolution-inspired optimization method that explicitly incorporates competitive interactions into deep network training. Unlike conventional sample reweighting strategies that rely mainly on predefined heuristics or static criteria, NS estimates the competitive status of each sample in a group-wise context and uses it to adaptively regulate its training contribution. Specifically, NS first assembles multiple samples into a composite image and rescales it to the original input size for model inference. Based on the resulting predictions, a natural selection score is computed for each sample to characterize its relative competitive variation within the constructed group. These scores are then used to dynamically reweight the sample-wise loss, thereby introducing an explicit competition-driven mechanism into the optimization process. In this way, NS provides a simple yet effective means of moving beyond uniform sample treatment and enables more adaptive and balanced model optimization. Extensive experiments on 12 public datasets across four image classification tasks demonstrate the effectiveness of the proposed method. Moreover, NS is compatible with diverse network architectures and does not depend on task-specific assumptions, indicating its strong generality and practical potential. The code will be made publicly available.

Huiping Zhuang, Yuchen Liu, Run He et al.

Online Class Incremental Learning (OCIL) aims to train models incrementally, where data arrive in mini-batches, and previous data are not accessible. A major challenge in OCIL is Catastrophic Forgetting, i.e., the loss of previously learned knowledge. Among existing baselines, replay-based methods show competitive results but requires extra memory for storing exemplars, while exemplar-free (i.e., data need not be stored for replay in production) methods are resource-friendly but often lack accuracy. In this paper, we propose an exemplar-free approach--Forward-only Online Analytic Learning (F-OAL). Unlike traditional methods, F-OAL does not rely on back-propagation and is forward-only, significantly reducing memory usage and computational time. Cooperating with a pre-trained frozen encoder with Feature Fusion, F-OAL only needs to update a linear classifier by recursive least square. This approach simultaneously achieves high accuracy and low resource consumption. Extensive experiments on benchmark datasets demonstrate F-OAL's robust performance in OCIL scenarios. Code is available at https://github.com/liuyuchen-cz/F-OAL.

Haoyu Zhu, Yi Zhang, Lei Yao et al.

Reconstructing high-fidelity 3D hands from egocentric monocular videos remains a challenge due to the limitations in capturing high-resolution geometry, hand-object interactions, and complex objects on hands. Additionally, existing methods often incur high computational costs, making them impractical for real-time applications. In this work, we propose Mesh-inellipse Aligned deformable Surfel Splatting (MASS) to address these challenges by leveraging a deformable 2D Gaussian Surfel representation. We introduce the mesh-aligned Steiner Inellipse and fractal densification for mesh-to-surfel conversion that initiates high-resolution 2D Gaussian surfels from coarse parametric hand meshes, providing surface representation with photorealistic rendering potential. Second, we propose Gaussian Surfel Deformation, which enables efficient modeling of hand deformations and personalized features by predicting residual updates to surfel attributes and introducing an opacity mask to refine geometry and texture without adaptive density control. In addition, we propose a two-stage training strategy and a novel binding loss to improve the optimization robustness and reconstruction quality. Extensive experiments on the ARCTIC dataset, the Hand Appearance dataset, and the Interhand2.6M dataset demonstrate that our model achieves superior reconstruction performance compared to state-of-the-art methods.

Lei Yao, Yong Chen, Yuejiao Su et al.

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 that leverages emerging multimodal large language models (MLLMs) for interaction intention-driven 3D affordance grounding, namely HAMMER. Instead of generating explicit object attribute descriptions or relying on off-the-shelf 2D segmenters, we alternatively aggregate the interaction intention depicted in the image into a contact-aware embedding and guide the model to infer textual affordance labels, ensuring it thoroughly excavates object semantics and contextual cues. We further devise a hierarchical cross-modal integration mechanism to fully exploit the complementary information from the MLLM for 3D representation refinement and introduce a multi-granular geometry lifting module that infuses spatial characteristics into the extracted intention embedding, thus facilitating accurate 3D affordance localization. Extensive experiments on public datasets and our newly constructed corrupted benchmark demonstrate the superiority and robustness of HAMMER compared to existing approaches. All code and weights are publicly available.

Junliang Chen, Huaiyuan Xu, Yi Wang et al.

Predicting variations in complex traffic environments is crucial for the safety of autonomous driving. Recent advancements in occupancy forecasting have enabled forecasting future 3D occupied status in driving environments by observing historical 2D images. However, high computational demands make occupancy forecasting less efficient during training and inference stages, hindering its feasibility for deployment on edge agents. In this paper, we propose a novel framework, i.e., OccProphet, to efficiently and effectively learn occupancy forecasting with significantly lower computational requirements while improving forecasting accuracy. OccProphet comprises three lightweight components: Observer, Forecaster, and Refiner. The Observer extracts spatio-temporal features from 3D multi-frame voxels using the proposed Efficient 4D Aggregation with Tripling-Attention Fusion, while the Forecaster and Refiner conditionally predict and refine future occupancy inferences. Experimental results on nuScenes, Lyft-Level5, and nuScenes-Occupancy datasets demonstrate that OccProphet is both training- and inference-friendly. OccProphet reduces 58\%$\sim$78\% of the computational cost with a 2.6$\times$ speedup compared with the state-of-the-art Cam4DOcc. Moreover, it achieves 4\%$\sim$18\% relatively higher forecasting accuracy. Code and models are publicly available at https://github.com/JLChen-C/OccProphet.

Sixu Lin, Junliang Chen, Huaiyuan Xu et al.

Planning and acting in 3D environments is a fundamental capability for robotic manipulation in the real world. Although prior work has explored predictive flow planners to guide 3D manipulation, existing approaches often rely on modular pipelines stacking multiple submodels, resulting in high computational overhead and limited real-time performance. To address these challenges, we introduce RoboFlow4D, a lightweight flow world model that unifies perception and planning by estimating temporal motion in physical 3D space. As an end-to-end framework, RoboFlow4D directly predicts multi-frame 3D flows from visual observations and textual instructions, providing explicit flow-based planning to guide action generation. This design allows seamless integration with general action policies, forming an efficient observation-planning-execution closed loop. Through slow-fast collaboration between flow prediction and action control, RoboFlow4D enables real-time and resource-efficient manipulation. Extensive experiments in both simulation and real-world settings demonstrate that RoboFlow4D consistently improves manipulation success rates and computational efficiency, advancing flow-guided planning for embodied intelligence.

Yi Zhang, Yi Wang, Lei Yao et al.

Image-based 3D object detection aims to identify and localize objects in 3D space using only RGB images, eliminating the need for expensive depth sensors required by point cloud-based methods. Existing image-based approaches face two critical challenges: methods achieving high accuracy typically require dense 3D supervision, while those operating without such supervision struggle to extract accurate geometry from images alone. In this paper, we present GVSynergy-Det, a novel framework that enhances 3D detection through synergistic Gaussian-Voxel representation learning. Our key insight is that continuous Gaussian and discrete voxel representations capture complementary geometric information: Gaussians excel at modeling fine-grained surface details while voxels provide structured spatial context. We introduce a dual-representation architecture that: 1) adapts generalizable Gaussian Splatting to extract complementary geometric features for detection tasks, and 2) develops a cross-representation enhancement mechanism that enriches voxel features with geometric details from Gaussian fields. Unlike previous methods that either rely on time-consuming per-scene optimization or utilize Gaussian representations solely for depth regularization, our synergistic strategy directly leverages features from both representations through learnable integration, enabling more accurate object localization. Extensive experiments demonstrate that GVSynergy-Det achieves state-of-the-art results on challenging indoor benchmarks, significantly outperforming existing methods on both ScanNetV2 and ARKitScenes datasets, all without requiring any depth or dense 3D geometry supervision (e.g., point clouds or TSDF).

Yuejiao Su, Xinshen Zhang, Zhen Ye et al.

Understanding human--environment interactions from egocentric vision is essential for assistive robotics and embodied intelligent agents, yet existing multimodal large language models (MLLMs) still struggle with accurate interaction reasoning and fine-grained pixel grounding. To this end, this paper introduces EARL, an Egocentric Analysis-guided Reinforcement Learning framework that explicitly transfers coarse interaction semantics to query-oriented answering and grounding. Specifically, EARL adopts a two-stage parsing framework including coarse-grained interpretation and fine-grained response. The first stage holistically interprets egocentric interactions and generates a structured textual description. The second stage produces the textual answer and pixel-level mask in response to the user query. To bridge the two stages, we extract a global interaction descriptor as a semantic prior, which is integrated via a novel Analysis-guided Feature Synthesizer (AFS) for query-oriented reasoning. To optimize heterogeneous outputs, including textual answers, bounding boxes, and grounding masks, we design a multi-faceted reward function and train the response stage with GRPO. Experiments on Ego-IRGBench show that EARL achieves 65.48% cIoU for pixel grounding, outperforming previous RL-based methods by 8.37%, while OOD grounding results on EgoHOS indicate strong transferability to unseen egocentric grounding scenarios.

Wenyang Liu, Chen Cai, Jianjun Gao et al.

Although the lightweight Vision Transformer has significantly advanced image super-resolution (SR), it faces the inherent challenge of a limited receptive field due to the window-based self-attention modeling. The quadratic computational complexity relative to window size restricts its ability to use a large window size for expanding the receptive field while maintaining low computational costs. To address this challenge, we propose PromptSR, a novel prompt-empowered lightweight image SR method. The core component is the proposed cascade prompting block (CPB), which enhances global information access and local refinement via three cascaded prompting layers: a global anchor prompting layer (GAPL) and two local prompting layers (LPLs). The GAPL leverages downscaled features as anchors to construct low-dimensional anchor prompts (APs) through cross-scale attention, significantly reducing computational costs. These APs, with enhanced global perception, are then used to provide global prompts, efficiently facilitating long-range token connections. The two LPLs subsequently combine category-based self-attention and window-based self-attention to refine the representation in a coarse-to-fine manner. They leverage attention maps from the GAPL as additional global prompts, enabling them to perceive features globally at different granularities for adaptive local refinement. In this way, the proposed CPB effectively combines global priors and local details, significantly enlarging the receptive field while maintaining the low computational costs of our PromptSR. The experimental results demonstrate the superiority of our method, which outperforms state-of-the-art lightweight SR methods in quantitative, qualitative, and complexity evaluations. Our code will be released at https://github.com/wenyang001/PromptSR.

Xiaoqi Wang, Yi Wang, Lap-Pui Chau

Egocentric video-language understanding demands both high efficiency and accurate spatial-temporal modeling. Existing approaches face three key challenges: 1) Excessive pre-training cost arising from multi-stage pre-training pipelines, 2) Ineffective spatial-temporal encoding due to manually split 3D rotary positional embeddings that hinder feature interactions, and 3) Imprecise learning objectives in soft-label multi-instance retrieval, which neglect negative pair correlations. In this paper, we introduce EVA02-AT, a suite of EVA02-based video-language foundation models tailored to egocentric video understanding tasks. EVA02-AT first efficiently transfers an image-based CLIP model into a unified video encoder via a single-stage pretraining. Second, instead of applying rotary positional embeddings to isolated dimensions, we introduce spatial-temporal rotary positional embeddings along with joint attention, which can effectively encode both spatial and temporal information on the entire hidden dimension. This joint encoding of spatial-temporal features enables the model to learn cross-axis relationships, which are crucial for accurately modeling motion and interaction in videos. Third, focusing on multi-instance video-language retrieval tasks, we introduce the Symmetric Multi-Similarity (SMS) loss and a novel training framework that advances all soft labels for both positive and negative pairs, providing a more precise learning objective. Extensive experiments on Ego4D, EPIC-Kitchens-100, and Charades-Ego under zero-shot and fine-tuning settings demonstrate that EVA02-AT achieves state-of-the-art performance across diverse egocentric video-language tasks with fewer parameters. Models with our SMS loss also show significant performance gains on multi-instance retrieval benchmarks. Our code and models are publicly available at https://github.com/xqwang14/EVA02-AT .

Junlong Li, Huaiyuan Xu, Sijie Cheng et al.

Driven by recent advances in vision language models (VLMs) and egocentric perception research, we introduce the concept of an egocentric procedural AI assistant (EgoProceAssist) tailored to step-by-step support daily procedural tasks in a first-person view. In this work, we start by identifying three core tasks: egocentric procedural error detection, egocentric procedural learning, and egocentric procedural question answering. These tasks define the essential functions of EgoProceAssist within a new taxonomy. Specifically, our work encompasses a comprehensive review of current techniques, relevant datasets, and evaluation metrics across these three core areas. To clarify the gap between the proposed EgoProceAssist and existing VLM-based AI assistants, we introduce novel experiments and provide a comprehensive evaluation of representative VLM-based methods. Based on these findings and our technical analysis, we discuss the challenges ahead and suggest future research directions. Furthermore, an exhaustive list of this study is publicly available in an active repository that continuously collects the latest work: https://github.com/z1oong/Building-Egocentric-Procedural-AI-Assistant

Xiaoqi Wang, Yi Wang, Lap-Pui Chau

In this report, we present our champion solution for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge in CVPR 2024. Essentially, this challenge differs from traditional visual-text retrieval tasks by providing a correlation matrix that acts as a set of soft labels for video-text clip combinations. However, existing loss functions have not fully exploited this information. Motivated by this, we propose a novel loss function, Symmetric Multi-Similarity Loss, which offers a more precise learning objective. Together with tricks and ensemble learning, the model achieves 63.76% average mAP and 74.25% average nDCG on the public leaderboard, demonstrating the effectiveness of our approach. Our code will be released at: https://github.com/xqwang14/SMS-Loss/tree/main

Haihan Tang, Yi Wang, Lap-Pui Chau

In this paper, we propose a three-stream adaptive fusion network named TAFNet, which uses paired RGB and thermal images for crowd counting. Specifically, TAFNet is divided into one main stream and two auxiliary streams. We combine a pair of RGB and thermal images to constitute the input of main stream. Two auxiliary streams respectively exploit RGB image and thermal image to extract modality-specific features. Besides, we propose an Information Improvement Module (IIM) to fuse the modality-specific features into the main stream adaptively. Experiment results on RGBT-CC dataset show that our method achieves more than 20% improvement on mean average error and root mean squared error compared with state-of-the-art method. The source code will be publicly available at https://github.com/TANGHAIHAN/TAFNet.

Nanyang Yang, Yi Wang, Lap-Pui Chau

The CenterTrack tracking algorithm achieves state-of-the-art tracking performance using a simple detection model and single-frame spatial offsets to localize objects and predict their associations in a single network. However, this joint detection and tracking method still suffers from high identity switches due to the inferior association method. To reduce the high number of identity switches and improve the tracking accuracy, in this paper, we propose to incorporate a simple tracked object bounding box and overlapping prediction based on the current frame onto the CenterTrack algorithm. Specifically, we propose an Intersection over Union (IOU) distance cost matrix in the association step instead of simple point displacement distance. We evaluate our proposed tracker on the MOT17 test dataset, showing that our proposed method can reduce identity switches significantly by 22.6% and obtain a notable improvement of 1.5% in IDF1 compared to the original CenterTrack's under the same tracklet lifetime. The source code is released at https://github.com/Nanyangny/CenterTrack-IOU.

Yi Wang, Xinyu Hou, Lap-Pui Chau

In this paper, we propose a simple yet effective crowd counting and localization network named SCALNet. Unlike most existing works that separate the counting and localization tasks, we consider those tasks as a pixel-wise dense prediction problem and integrate them into an end-to-end framework. Specifically, for crowd counting, we adopt a counting head supervised by the Mean Square Error (MSE) loss. For crowd localization, the key insight is to recognize the keypoint of people, i.e., the center point of heads. We propose a localization head to distinguish dense crowds trained by two loss functions, i.e., Negative-Suppressed Focal (NSF) loss and False-Positive (FP) loss, which balances the positive/negative examples and handles the false-positive predictions. Experiments on the recent and large-scale benchmark, NWPU-Crowd, show that our approach outperforms the state-of-the-art methods by more than 5% and 10% improvement in crowd localization and counting tasks, respectively. The code is publicly available at https://github.com/WangyiNTU/SCALNet.

Yi Wang, Junhui Hou, Xinyu Hou et al.

In this paper, we propose a novel self-training approach named Crowd-SDNet that enables a typical object detector trained only with point-level annotations (i.e., objects are labeled with points) to estimate both the center points and sizes of crowded objects. Specifically, during training, we utilize the available point annotations to supervise the estimation of the center points of objects directly. Based on a locally-uniform distribution assumption, we initialize pseudo object sizes from the point-level supervisory information, which are then leveraged to guide the regression of object sizes via a crowdedness-aware loss. Meanwhile, we propose a confidence and order-aware refinement scheme to continuously refine the initial pseudo object sizes such that the ability of the detector is increasingly boosted to detect and count objects in crowds simultaneously. Moreover, to address extremely crowded scenes, we propose an effective decoding method to improve the detector's representation ability. Experimental results on the WiderFace benchmark show that our approach significantly outperforms state-of-the-art point-supervised methods under both detection and counting tasks, i.e., our method improves the average precision by more than 10% and reduces the counting error by 31.2%. Besides, our method obtains the best results on the crowd counting and localization datasets (i.e., ShanghaiTech and NWPU-Crowd) and vehicle counting datasets (i.e., CARPK and PUCPR+) compared with state-of-the-art counting-by-detection methods. The code will be publicly available at https://github.com/WangyiNTU/Point-supervised-crowd-detection.

Alexander Matyasko, Lap-Pui Chau

Ideally, what confuses neural network should be confusing to humans. However, recent experiments have shown that small, imperceptible perturbations can change the network prediction. To address this gap in perception, we propose a novel approach for learning robust classifier. Our main idea is: adversarial examples for the robust classifier should be indistinguishable from the regular data of the adversarial target. We formulate a problem of learning robust classifier in the framework of Generative Adversarial Networks (GAN), where the adversarial attack on classifier acts as a generator, and the critic network learns to distinguish between regular and adversarial images. The classifier cost is augmented with the objective that its adversarial examples should confuse the adversary critic. To improve the stability of the adversarial mapping, we introduce adversarial cycle-consistency constraint which ensures that the adversarial mapping of the adversarial examples is close to the original. In the experiments, we show the effectiveness of our defense. Our method surpasses in terms of robustness networks trained with adversarial training. Additionally, we verify in the experiments with human annotators on MTurk that adversarial examples are indeed visually confusing. Codes for the project are available at https://github.com/aam-at/adversary_critic.

Wenyang Liu, Kejun Wu, Tianyi Liu et al.

Multimedia file fragment classification (MFFC) aims to identify file fragment types, e.g., image/video, audio, and text without system metadata. It is of vital importance in multimedia storage and communication. Existing MFFC methods typically treat fragments as 1D byte sequences and emphasize the relations between separate bytes (interbytes) for classification. However, the more informative relations inside bytes (intrabytes) are overlooked and seldom investigated. By looking inside bytes, the bit-level details of file fragments can be accessed, enabling a more accurate classification. Motivated by this, we first propose Byte2Image, a novel visual representation model that incorporates previously overlooked intrabyte information into file fragments and reinterprets these fragments as 2D grayscale images. This model involves a sliding byte window to reveal the intrabyte information and a rowwise stacking of intrabyte ngrams for embedding fragments into a 2D space. Thus, complex interbyte and intrabyte correlations can be mined simultaneously using powerful vision networks. Additionally, we propose an end-to-end dual-branch network ByteNet to enhance robust correlation mining and feature representation. ByteNet makes full use of the raw 1D byte sequence and the converted 2D image through a shallow byte branch feature extraction (BBFE) and a deep image branch feature extraction (IBFE) network. In particular, the BBFE, composed of a single fully-connected layer, adaptively recognizes the co-occurrence of several some specific bytes within the raw byte sequence, while the IBFE, built on a vision Transformer, effectively mines the complex interbyte and intrabyte correlations from the converted image. Experiments on the two representative benchmarks, including 14 cases, validate that our proposed method outperforms state-of-the-art approaches on different cases by up to 12.2%.

Yuejiao Su, Yi Wang, Qiongyang Hu et al.

Egocentric interaction perception is one of the essential branches in investigating human-environment interaction, which lays the basis for developing next-generation intelligent systems. However, existing egocentric interaction understanding methods cannot yield coherent textual and pixel-level responses simultaneously according to user queries, which lacks flexibility for varying downstream application requirements. To comprehend egocentric interactions exhaustively, this paper presents a novel task named Egocentric Interaction Reasoning and pixel Grounding (Ego-IRG). Taking an egocentric image with the query as input, Ego-IRG is the first task that aims to resolve the interactions through three crucial steps: analyzing, answering, and pixel grounding, which results in fluent textual and fine-grained pixel-level responses. Another challenge is that existing datasets cannot meet the conditions for the Ego-IRG task. To address this limitation, this paper creates the Ego-IRGBench dataset based on extensive manual efforts, which includes over 20k egocentric images with 1.6 million queries and corresponding multimodal responses about interactions. Moreover, we design a unified ANNEXE model to generate text- and pixel-level outputs utilizing multimodal large language models, which enables a comprehensive interpretation of egocentric interactions. The experiments on the Ego-IRGBench exhibit the effectiveness of our ANNEXE model compared with other works.

Kunyuan Deng, Yi Wang, Lap-Pui Chau

Egocentric human-object interaction (Ego-HOI) detection is crucial for intelligent agents to understand and assist human activities from a first-person perspective. However, progress has been hindered by the lack of benchmarks and methods tailored to egocentric challenges such as severe hand-object occlusion. In this paper, we introduce the real-world Ego-HOI detection task and the accompanying Ego-HOIBench, a new dataset with over 27K egocentric images and explicit, fine-grained hand-verb-object triplet annotations across 123 categories. Ego-HOIBench covers diverse daily scenarios, object types, and both single- and two-hand interactions, offering a comprehensive testbed for Ego-HOI research. Benchmarking existing third-person HOI detectors on Ego-HOIBench reveals significant performance gaps, highlighting the need for egocentric-specific solutions. To this end, we propose Hand Geometry and Interactivity Refinement (HGIR), a lightweight, plug-and-play scheme that leverages hand pose and geometric cues to enhance interaction representations. Specifically, HGIR explicitly extracts global hand geometric features from the estimated hand pose proposals, and further refines interaction features through pose-interaction attention, enabling the model to focus on subtle hand-object relationship differences even under severe occlusion. HGIR significantly improves Ego-HOI detection performance across multiple baselines, achieving new state-of-the-art results on Ego-HOIBench. Our dataset and method establish a solid foundation for future research in egocentric vision and human-object interaction understanding. Project page: https://dengkunyuan.github.io/EgoHOIBench/

Ying Zheng, Yiyi Zhang, Yi Wang et al.

Source-free domain adaptation in visual emotion recognition (SFDA-VER) is a highly challenging task that requires adapting VER models to the target domain without relying on source data, which is of great significance for data privacy protection. However, due to the unignorable disparities between visual emotion data and traditional image classification data, existing SFDA methods perform poorly on this task. In this paper, we investigate the SFDA-VER task from a fuzzy perspective and identify two key issues: fuzzy emotion labels and fuzzy pseudo-labels. These issues arise from the inherent uncertainty of emotion annotations and the potential mispredictions in pseudo-labels. To address these issues, we propose a novel fuzzy-aware loss (FAL) to enable the VER model to better learn and adapt to new domains under fuzzy labels. Specifically, FAL modifies the standard cross entropy loss and focuses on adjusting the losses of non-predicted categories, which prevents a large number of uncertain or incorrect predictions from overwhelming the VER model during adaptation. In addition, we provide a theoretical analysis of FAL and prove its robustness in handling the noise in generated pseudo-labels. Extensive experiments on 26 domain adaptation sub-tasks across three benchmark datasets demonstrate the effectiveness of our method.

Chuang Yang, Xu Han, Tao Han et al.

Traffic signs play a key role in assisting autonomous driving systems (ADS) by enabling the assessment of vehicle behavior in compliance with traffic regulations and providing navigation instructions. However, current works are limited to basic sign understanding without considering the egocentric vehicle's spatial position, which fails to support further regulation assessment and direction navigation. Following the above issues, we introduce a new task: traffic sign interpretation from the vehicle's first-person view, referred to as TSI-FPV. Meanwhile, we develop a traffic guidance assistant (TGA) scenario application to re-explore the role of traffic signs in ADS as a complement to popular autonomous technologies (such as obstacle perception). Notably, TGA is not a replacement for electronic map navigation; rather, TGA can be an automatic tool for updating it and complementing it in situations such as offline conditions or temporary sign adjustments. Lastly, a spatial and semantic logic-aware stepwise reasoning pipeline (SignEye) is constructed to achieve the TSI-FPV and TGA, and an application-specific dataset (Traffic-CN) is built. Experiments show that TSI-FPV and TGA are achievable via our SignEye trained on Traffic-CN. The results also demonstrate that the TGA can provide complementary information to ADS beyond existing popular autonomous technologies.

Run He, Di Fang, Yizhu Chen et al.

Exemplar-free class-incremental learning (EFCIL) aims to mitigate catastrophic forgetting in class-incremental learning (CIL) without available historical training samples as exemplars. Compared with its exemplar-based CIL counterpart that stores exemplars, EFCIL suffers more from forgetting issues. Recently, a new EFCIL branch named Analytic Continual Learning (ACL) introduces a gradient-free paradigm via Recursive Least-Square, achieving a forgetting-resistant classifier training with a frozen backbone during CIL. However, existing ACL suffers from ineffective representations and insufficient utilization of backbone knowledge. In this paper, we propose a representation-enhanced analytic learning (REAL) to address these problems. To enhance the representation, REAL constructs a dual-stream base pretraining followed by representation enhancing distillation process. The dual-stream base pretraining combines self-supervised contrastive learning for general features and supervised learning for class-specific knowledge, followed by the representation enhancing distillation to merge both streams, enhancing representations for subsequent CIL paradigm. To utilize more knowledge from the backbone, REAL presents a feature fusion buffer to multi-layer backbone features, providing informative features for the subsequent classifier training. Our method can be incorporated into existing ACL techniques and provides more competitive performance. Empirical results demonstrate that, REAL achieves state-of-the-art performance on CIFAR-100, ImageNet-100 and ImageNet-1k benchmarks, outperforming exemplar-free methods and rivaling exemplar-based approaches.

Lei Yao, Yi Wang, Yi Zhang et al.

The significance of informative and robust point representations has been widely acknowledged for 3D scene understanding. Despite existing self-supervised pre-training counterparts demonstrating promising performance, the model collapse and structural information deficiency remain prevalent due to insufficient point discrimination difficulty, yielding unreliable expressions and suboptimal performance. In this paper, we present GaussianCross, a novel cross-modal self-supervised 3D representation learning architecture integrating feed-forward 3D Gaussian Splatting (3DGS) techniques to address current challenges. GaussianCross seamlessly converts scale-inconsistent 3D point clouds into a unified cuboid-normalized Gaussian representation without missing details, enabling stable and generalizable pre-training. Subsequently, a tri-attribute adaptive distillation splatting module is incorporated to construct a 3D feature field, facilitating synergetic feature capturing of appearance, geometry, and semantic cues to maintain cross-modal consistency. To validate GaussianCross, we perform extensive evaluations on various benchmarks, including ScanNet, ScanNet200, and S3DIS. In particular, GaussianCross shows a prominent parameter and data efficiency, achieving superior performance through linear probing (<0.1% parameters) and limited data training (1% of scenes) compared to state-of-the-art methods. Furthermore, GaussianCross demonstrates strong generalization capabilities, improving the full fine-tuning accuracy by 9.3% mIoU and 6.1% AP$_{50}$ on ScanNet200 semantic and instance segmentation tasks, respectively, supporting the effectiveness of our approach. The code, weights, and visualizations are publicly available at \href{https://rayyoh.github.io/GaussianCross/}{https://rayyoh.github.io/GaussianCross/}.