BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Chi-Man Pun

Chi-Man Pun contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computer VisionMultimediaArtificial IntelligenceCryptography and Securityeess.ASInformation RetrievalMachine LearningSound

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
12works
0followers
8topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

12 published item(s)

preprint2026arXiv

Control Your View: High-Resolution Global Semantic Manipulation in Learned Image Compression

Learned image compression (LIC) integrates deep neural networks (DNNs) to map high-dimensional images into compact latent representations, reducing redundancy and achieving superior rate-distortion (RD) performance in benign settings. Unfortunately, due to inherent vulnerabilities in DNNs, LIC systems are susceptible to adversarial perturbations that lead to downstream deterioration, compression rate degradation, untargeted distortion, and both local semantic manipulation (LSM) and low-resolution ($3\times28\times28$) global semantic manipulation (GSM). However, high-resolution GSM remains unexplored due to its intractability. Notably, the existing project gradient descent (PGD) method achieves near-perfect white-box attacks for classification, segmentation, and other tasks, yet fails to generalize to high-resolution GSM. Our theoretical and empirical analyses reveal that well-performing GSM drives adversarial examples from the Identity Region to the Amplification Region through the Lazying-Oscillating-Refining stages. General $\ell_{\infty}$-bounded attacks fail on high-resolution GSM because their step-size schedules cannot accommodate both the Oscillating and Refining stages. Based on this, we propose the Periodic Geometric Decay schedule that enables $\ell_{\infty}$-bounded high-resolution GSM. To verify our approach, we integrate it with PGD, yielding a minimal variant, PGD$^{2}$-GSM. Extensive experiments on the Kodak $(3\times768\times512)$ demonstrate that our PGD$^{2}$-GSM is the first to stably achieve high-resolution GSM, thereby exposing a novel threat to LIC systems. Code is available at https://github.com/chinaliangjiaming/PGD2-GSM.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

IO-RAE: Information-Obfuscation Reversible Adversarial Example for Audio Privacy Protection

The rapid advancements in artificial intelligence have significantly accelerated the adoption of speech recognition technology, leading to its widespread integration across various applications. However, this surge in usage also highlights a critical issue: audio data is highly vulnerable to unauthorized exposure and analysis, posing significant privacy risks for businesses and individuals. This paper introduces an Information-Obfuscation Reversible Adversarial Example (IO-RAE) framework, the pioneering method designed to safeguard audio privacy using reversible adversarial examples. IO-RAE leverages large language models to generate misleading yet contextually coherent content, effectively preventing unauthorized eavesdropping by humans and Automatic Speech Recognition (ASR) systems. Additionally, we propose the Cumulative Signal Attack technique, which mitigates high-frequency noise and enhances attack efficacy by targeting low-frequency signals. Our approach ensures the protection of audio data without degrading its quality or our ability. Experimental evaluations demonstrate the superiority of our method, achieving a targeted misguidance rate of 96.5% and a remarkable 100% untargeted misguidance rate in obfuscating target keywords across multiple ASR models, including a commercial black-box system from Google. Furthermore, the quality of the recovered audio, measured by the Perceptual Evaluation of Speech Quality score, reached 4.45, comparable to high-quality original recordings. Notably, the recovered audio processed by ASR systems exhibited an error rate of 0%, indicating nearly lossless recovery. These results highlight the practical applicability and effectiveness of our IO-RAE framework in protecting sensitive audio privacy.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

TopoMamba: Topology-Aware Scanning and Fusion for Segmenting Heterogeneous Medical Visual Media

Visual state-space models (SSMs) have shown strong potential for medical image segmentation, yet their effectiveness is often limited by two practical issues: axis-biased scan ordering weakens the modeling of oblique and curved structures, and naive multi-branch fusion tends to amplify redundant responses. We present TopoMamba, a topology-aware scan-and-fuse framework for segmenting heterogeneous medical visual media. The method combines a diagonal/anti-diagonal TopoA-Scan branch with the standard Cross-Scan branch to provide complementary structural priors, and introduces ScanCache, a device-aware caching mechanism that amortizes explicit scan-index construction across recurring resolutions. To fuse heterogeneous scan features efficiently, we further propose a lightweight HSIC Gate that regulates branch interaction using a dependence-aware scalar gating rule. We also instantiate a volumetric TopoMamba-3D for practical 3D clinical segmentation. Experiments on Synapse CT, ISIC 2017 dermoscopy, and CVC-ClinicDB endoscopy show that TopoMamba consistently improves segmentation quality over strong CNN, Transformer, and SSM baselines, with particularly clear gains on thin or curved targets such as the pancreas and gallbladder, while maintaining favorable deployment efficiency under dynamic input resolutions. These results suggest that topology-aware scan ordering and lightweight dependence-aware fusion form an effective and practical design for medical multimedia segmentation. The code will be made publicly available.

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

COMMA: Co-Articulated Multi-Modal Learning

Pretrained large-scale vision-language models such as CLIP have demonstrated excellent generalizability over a series of downstream tasks. However, they are sensitive to the variation of input text prompts and need a selection of prompt templates to achieve satisfactory performance. Recently, various methods have been proposed to dynamically learn the prompts as the textual inputs to avoid the requirements of laboring hand-crafted prompt engineering in the fine-tuning process. We notice that these methods are suboptimal in two aspects. First, the prompts of the vision and language branches in these methods are usually separated or uni-directionally correlated. Thus, the prompts of both branches are not fully correlated and may not provide enough guidance to align the representations of both branches. Second, it's observed that most previous methods usually achieve better performance on seen classes but cause performance degeneration on unseen classes compared to CLIP. This is because the essential generic knowledge learned in the pretraining stage is partly forgotten in the fine-tuning process. In this paper, we propose Co-Articulated Multi-Modal Learning (COMMA) to handle the above limitations. Especially, our method considers prompts from both branches to generate the prompts to enhance the representation alignment of both branches. Besides, to alleviate forgetting about the essential knowledge, we minimize the feature discrepancy between the learned prompts and the embeddings of hand-crafted prompts in the pre-trained CLIP in the late transformer layers. We evaluate our method across three representative tasks of generalization to novel classes, new target datasets and unseen domain shifts. Experimental results demonstrate the superiority of our method by exhibiting a favorable performance boost upon all tasks with high efficiency.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Asymmetric Scalable Cross-modal Hashing

Cross-modal hashing is a successful method to solve large-scale multimedia retrieval issue. A lot of matrix factorization-based hashing methods are proposed. However, the existing methods still struggle with a few problems, such as how to generate the binary codes efficiently rather than directly relax them to continuity. In addition, most of the existing methods choose to use an $n\times n$ similarity matrix for optimization, which makes the memory and computation unaffordable. In this paper we propose a novel Asymmetric Scalable Cross-Modal Hashing (ASCMH) to address these issues. It firstly introduces a collective matrix factorization to learn a common latent space from the kernelized features of different modalities, and then transforms the similarity matrix optimization to a distance-distance difference problem minimization with the help of semantic labels and common latent space. Hence, the computational complexity of the $n\times n$ asymmetric optimization is relieved. In the generation of hash codes we also employ an orthogonal constraint of label information, which is indispensable for search accuracy. So the redundancy of computation can be much reduced. For efficient optimization and scalable to large-scale datasets, we adopt the two-step approach rather than optimizing simultaneously. Extensive experiments on three benchmark datasets: Wiki, MIRFlickr-25K, and NUS-WIDE, demonstrate that our ASCMH outperforms the state-of-the-art cross-modal hashing methods in terms of accuracy and efficiency.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Learning Enriched Illuminants for Cross and Single Sensor Color Constancy

Color constancy aims to restore the constant colors of a scene under different illuminants. However, due to the existence of camera spectral sensitivity, the network trained on a certain sensor, cannot work well on others. Also, since the training datasets are collected in certain environments, the diversity of illuminants is limited for complex real world prediction. In this paper, we tackle these problems via two aspects. First, we propose cross-sensor self-supervised training to train the network. In detail, we consider both the general sRGB images and the white-balanced RAW images from current available datasets as the white-balanced agents. Then, we train the network by randomly sampling the artificial illuminants in a sensor-independent manner for scene relighting and supervision. Second, we analyze a previous cascaded framework and present a more compact and accurate model by sharing the backbone parameters with learning attention specifically. Experiments show that our cross-sensor model and single-sensor model outperform other state-of-the-art methods by a large margin on cross and single sensor evaluations, respectively, with only 16% parameters of the previous best model.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Reversible Data Hiding in Encrypted Images by Lossless Pixel Conversion

Reversible data hiding in encrypted image (RDHEI) becomes a hot topic, and a lot of algorithms have been proposed to optimize this technology. However, these algorithms cannot achieve strong embedding capacity. Thus, in this paper, we propose an advanced RDHEI scheme based on lossless pixel conversion (LPC). Different from the previous RDHEI algorithms, LPC is inspired by the planar map coloring question, and it performs a dynamic image division process to divide the original image into irregular regions instead of regular blocks as in the previous RDHEI algorithms. In the process of LPC, pixel conversion is performed by region; that is, pixels in the same regions are converted to the same conversion values, which will occupy a smaller size, and then the available room can be reserved to accommodate additional data. LPC is a reversible process, so the original image can be losslessly recovered on the receiver side. Experimental results show that the embedding capacity of the proposed scheme outperforms the existing RDHEI algorithms.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

News Image Steganography: A Novel Architecture Facilitates the Fake News Identification

A larger portion of fake news quotes untampered images from other sources with ulterior motives rather than conducting image forgery. Such elaborate engraftments keep the inconsistency between images and text reports stealthy, thereby, palm off the spurious for the genuine. This paper proposes an architecture named News Image Steganography (NIS) to reveal the aforementioned inconsistency through image steganography based on GAN. Extractive summarization about a news image is generated based on its source texts, and a learned steganographic algorithm encodes and decodes the summarization of the image in a manner that approaches perceptual invisibility. Once an encoded image is quoted, its source summarization can be decoded and further presented as the ground truth to verify the quoting news. The pairwise encoder and decoder endow images of the capability to carry along their imperceptible summarization. Our NIS reveals the underlying inconsistency, thereby, according to our experiments and investigations, contributes to the identification accuracy of fake news that engrafts untampered images.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Personal Privacy Protection via Irrelevant Faces Tracking and Pixelation in Video Live Streaming

To date, the privacy-protection intended pixelation tasks are still labor-intensive and yet to be studied. With the prevailing of video live streaming, establishing an online face pixelation mechanism during streaming is an urgency. In this paper, we develop a new method called Face Pixelation in Video Live Streaming (FPVLS) to generate automatic personal privacy filtering during unconstrained streaming activities. Simply applying multi-face trackers will encounter problems in target drifting, computing efficiency, and over-pixelation. Therefore, for fast and accurate pixelation of irrelevant people's faces, FPVLS is organized in a frame-to-video structure of two core stages. On individual frames, FPVLS utilizes image-based face detection and embedding networks to yield face vectors. In the raw trajectories generation stage, the proposed Positioned Incremental Affinity Propagation (PIAP) clustering algorithm leverages face vectors and positioned information to quickly associate the same person's faces across frames. Such frame-wise accumulated raw trajectories are likely to be intermittent and unreliable on video level. Hence, we further introduce the trajectory refinement stage that merges a proposal network with the two-sample test based on the Empirical Likelihood Ratio (ELR) statistic to refine the raw trajectories. A Gaussian filter is laid on the refined trajectories for final pixelation. On the video live streaming dataset we collected, FPVLS obtains satisfying accuracy, real-time efficiency, and contains the over-pixelation problems.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Privacy-sensitive Objects Pixelation for Live Video Streaming

With the prevailing of live video streaming, establishing an online pixelation method for privacy-sensitive objects is an urgency. Caused by the inaccurate detection of privacy-sensitive objects, simply migrating the tracking-by-detection structure into the online form will incur problems in target initialization, drifting, and over-pixelation. To cope with the inevitable but impacting detection issue, we propose a novel Privacy-sensitive Objects Pixelation (PsOP) framework for automatic personal privacy filtering during live video streaming. Leveraging pre-trained detection networks, our PsOP is extendable to any potential privacy-sensitive objects pixelation. Employing the embedding networks and the proposed Positioned Incremental Affinity Propagation (PIAP) clustering algorithm as the backbone, our PsOP unifies the pixelation of discriminating and indiscriminating pixelation objects through trajectories generation. In addition to the pixelation accuracy boosting, experiments on the streaming video data we built show that the proposed PsOP can significantly reduce the over-pixelation ratio in privacy-sensitive object pixelation.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Defocus Blur Detection via Depth Distillation

Defocus Blur Detection(DBD) aims to separate in-focus and out-of-focus regions from a single image pixel-wisely. This task has been paid much attention since bokeh effects are widely used in digital cameras and smartphone photography. However, identifying obscure homogeneous regions and borderline transitions in partially defocus images is still challenging. To solve these problems, we introduce depth information into DBD for the first time. When the camera parameters are fixed, we argue that the accuracy of DBD is highly related to scene depth. Hence, we consider the depth information as the approximate soft label of DBD and propose a joint learning framework inspired by knowledge distillation. In detail, we learn the defocus blur from ground truth and the depth distilled from a well-trained depth estimation network at the same time. Thus, the sharp region will provide a strong prior for depth estimation while the blur detection also gains benefits from the distilled depth. Besides, we propose a novel decoder in the fully convolutional network(FCN) as our network structure. In each level of the decoder, we design the Selective Reception Field Block(SRFB) for merging multi-scale features efficiently and reuse the side outputs as Supervision-guided Attention Block(SAB). Unlike previous methods, the proposed decoder builds reception field pyramids and emphasizes salient regions simply and efficiently. Experiments show that our approach outperforms 11 other state-of-the-art methods on two popular datasets. Our method also runs at over 30 fps on a single GPU, which is 2x faster than previous works. The code is available at: https://github.com/vinthony/depth-distillation

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Improving the Harmony of the Composite Image by Spatial-Separated Attention Module

Image composition is one of the most important applications in image processing. However, the inharmonious appearance between the spliced region and background degrade the quality of the image. Thus, we address the problem of Image Harmonization: Given a spliced image and the mask of the spliced region, we try to harmonize the "style" of the pasted region with the background (non-spliced region). Previous approaches have been focusing on learning directly by the neural network. In this work, we start from an empirical observation: the differences can only be found in the spliced region between the spliced image and the harmonized result while they share the same semantic information and the appearance in the non-spliced region. Thus, in order to learn the feature map in the masked region and the others individually, we propose a novel attention module named Spatial-Separated Attention Module (S2AM). Furthermore, we design a novel image harmonization framework by inserting the S2AM in the coarser low-level features of the Unet structure in two different ways. Besides image harmonization, we make a big step for harmonizing the composite image without the specific mask under previous observation. The experiments show that the proposed S2AM performs better than other state-of-the-art attention modules in our task. Moreover, we demonstrate the advantages of our model against other state-of-the-art image harmonization methods via criteria from multiple points of view. Code is available at https://github.com/vinthony/s2am

0 citations0 reviewsNo code linkedOpen access