W. K. Chan
YOU?
Author Swipe
View article: Scalable and Precise Patch Robustness Certification for Deep Learning Models with Top-k Predictions
Scalable and Precise Patch Robustness Certification for Deep Learning Models with Top-k Predictions Open
Patch robustness certification is an emerging verification approach for defending against adversarial patch attacks with provable guarantees for deep learning systems. Certified recovery techniques guarantee the prediction of the sole true…
View article: Context-Aware Fuzzing for Robustness Enhancement of Deep Learning Models
Context-Aware Fuzzing for Robustness Enhancement of Deep Learning Models Open
In the testing-retraining pipeline for enhancing the robustness property of deep learning (DL) models, many state-of-the-art robustness-oriented fuzzing techniques are metric-oriented. The pipeline generates adversarial examples as test ca…
View article: A3Rank: Augmentation Alignment Analysis for Prioritizing Overconfident Failing Samples for Deep Learning Models
A3Rank: Augmentation Alignment Analysis for Prioritizing Overconfident Failing Samples for Deep Learning Models Open
Sharpening deep learning models by training them with examples close to the decision boundary is a well-known best practice. Nonetheless, these models are still error-prone in producing predictions. In practice, the inference of the deep l…
View article: Context-Aware Fuzzing for Robustness Enhancement of Deep Learning Models
Context-Aware Fuzzing for Robustness Enhancement of Deep Learning Models Open
In the testing-retraining pipeline for enhancing the robustness property of deep learning (DL) models, many state-of-the-art robustness-oriented fuzzing techniques are metric-oriented. The pipeline generates adversarial examples as test ca…
View article: Multimodal LLM-based Query Paraphrasing for Video Search
Multimodal LLM-based Query Paraphrasing for Video Search Open
Text-to-video retrieval answers user queries through searches based on concepts and embeddings. However, due to limitations in the size of the concept bank and the amount of training data, answering queries in the wild is not always effect…
View article: Improving Interpretable Embeddings for Ad-hoc Video Search with Generative Captions and Multi-word Concept Bank
Improving Interpretable Embeddings for Ad-hoc Video Search with Generative Captions and Multi-word Concept Bank Open
Aligning a user query and video clips in cross-modal latent space and that with semantic concepts are two mainstream approaches for ad-hoc video search (AVS). However, the effectiveness of existing approaches is bottlenecked by the small s…
View article: CrossCert: A Cross-Checking Detection Approach to Patch Robustness Certification for Deep Learning Models
CrossCert: A Cross-Checking Detection Approach to Patch Robustness Certification for Deep Learning Models Open
Patch robustness certification is an emerging kind of defense technique against adversarial patch attacks with provable guarantees. There are two research lines: certified recovery and certified detection. They aim to label malicious sampl…
View article: Improving Interpretable Embeddings for Ad-hoc Video Search with Generative Captions and Multi-word Concept Bank
Improving Interpretable Embeddings for Ad-hoc Video Search with Generative Captions and Multi-word Concept Bank Open
Aligning a user query and video clips in cross-modal latent space and that with semantic concepts are two mainstream approaches for ad-hoc video search (AVS). However, the effectiveness of existing approaches is bottlenecked by the small s…
View article: IEEE Transactions on Systems, Man, and Cybernetics publication information
IEEE Transactions on Systems, Man, and Cybernetics publication information Open
View article: IEEE Transactions on Systems, Man, and Cybernetics publication information
IEEE Transactions on Systems, Man, and Cybernetics publication information Open
View article: (Un)likelihood Training for Interpretable Embedding
(Un)likelihood Training for Interpretable Embedding Open
Cross-modal representation learning has become a new normal for bridging the semantic gap between text and visual data. Learning modality agnostic representations in a continuous latent space, however, is often treated as a black-box data-…
View article: Identifying metamorphic relations: A data mutation directed approach
Identifying metamorphic relations: A data mutation directed approach Open
Summary Metamorphic testing (MT) is an effective technique to alleviate the test oracle problem. The principle of MT is to detect failures by checking whether some necessary properties, commonly known as metamorphic relations (MRs), of sof…
View article: IEEE Transactions on Systems, Man, and Cybernetics publication information
IEEE Transactions on Systems, Man, and Cybernetics publication information Open
View article: A study on the impact of pre-trained model on Just-In-Time defect prediction
A study on the impact of pre-trained model on Just-In-Time defect prediction Open
Previous researchers conducting Just-In-Time (JIT) defect prediction tasks have primarily focused on the performance of individual pre-trained models, without exploring the relationship between different pre-trained models as backbones. In…
View article: GroundNLQ @ Ego4D Natural Language Queries Challenge 2023
GroundNLQ @ Ego4D Natural Language Queries Challenge 2023 Open
In this report, we present our champion solution for Ego4D Natural Language Queries (NLQ) Challenge in CVPR 2023. Essentially, to accurately ground in a video, an effective egocentric feature extractor and a powerful grounding model are re…
View article: DeepPatch: Maintaining Deep Learning Model Programs to Retain Standard Accuracy with Substantial Robustness Improvement
DeepPatch: Maintaining Deep Learning Model Programs to Retain Standard Accuracy with Substantial Robustness Improvement Open
Maintaining a deep learning (DL) model by making the model substantially more robust through retraining with plenty of adversarial examples of non-trivial perturbation strength often reduces the model’s standard accuracy. Many existing mod…
View article: Program Committee
Program Committee Open
View article: Cross-domain Food Image-to-Recipe Retrieval by Weighted Adversarial Learning
Cross-domain Food Image-to-Recipe Retrieval by Weighted Adversarial Learning Open
Food image-to-recipe aims to learn an embedded space linking the rich semantics in recipes with the visual content in food image for cross-modal retrieval. The existing research works carry out the learning of such space by assuming that a…
View article: IEEE Transactions on Systems, Man, and Cybernetics publication information
IEEE Transactions on Systems, Man, and Cybernetics publication information Open
View article: CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding
CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding Open
Zhijian Hou, Wanjun Zhong, Lei Ji, Difei Gao, Kun Yan, W.k. Chan, Chong-Wah Ngo, Mike Zheng Shou, Nan Duan. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.
View article: IEEE Transactions on Systems, Man, and Cybernetics Publication Information
IEEE Transactions on Systems, Man, and Cybernetics Publication Information Open
View article: An Efficient COarse-to-fiNE Alignment Framework @ Ego4D Natural Language Queries Challenge 2022
An Efficient COarse-to-fiNE Alignment Framework @ Ego4D Natural Language Queries Challenge 2022 Open
This technical report describes the CONE approach for Ego4D Natural Language Queries (NLQ) Challenge in ECCV 2022. We leverage our model CONE, an efficient window-centric COarse-to-fiNE alignment framework. Specifically, CONE dynamically s…
View article: CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding
CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Grounding Open
This paper tackles an emerging and challenging problem of long video temporal grounding~(VTG) that localizes video moments related to a natural language (NL) query. Compared with short videos, long videos are also highly demanded but less …
View article: Introduction to the Special Issue on Software-Intensive Autonomous Systems: Methods and applications
Introduction to the Special Issue on Software-Intensive Autonomous Systems: Methods and applications Open
View article: IEEE Transactions on Systems, Man, and Cybernetics publication information
IEEE Transactions on Systems, Man, and Cybernetics publication information Open
View article: IEEE Transactions on Systems, Man, and Cybernetics publication information
IEEE Transactions on Systems, Man, and Cybernetics publication information Open
View article: IEEE Transactions on Systems, Man, and Cybernetics publication information
IEEE Transactions on Systems, Man, and Cybernetics publication information Open
View article: (Un)likelihood Training for Interpretable Embedding
(Un)likelihood Training for Interpretable Embedding Open
Cross-modal representation learning has become a new normal for bridging the semantic gap between text and visual data. Learning modality agnostic representations in a continuous latent space, however, is often treated as a black-box data-…
View article: Davida: A Decentralization Approach to Localizing Transaction Sequences for Debugging Transactional Atomicity Violations
Davida: A Decentralization Approach to Localizing Transaction Sequences for Debugging Transactional Atomicity Violations Open
Atomicity is a desirable property for multithreaded programs. In such programs, a transaction is an execution of an atomic code region that may contain memory accesses on an arbitrary number of shared variables. When transactions are not c…
View article: Cross-lingual Adaptation for Recipe Retrieval with Mixup
Cross-lingual Adaptation for Recipe Retrieval with Mixup Open
Cross-modal recipe retrieval has attracted research attention in recent years, thanks to the availability of large-scale paired data for training. Nevertheless, obtaining adequate recipe-image pairs covering the majority of cuisines for su…