3 citations · 6 across the 19 of their papers we have counts for
21 papers
Cog-VADU: A Training-Free Cognitive Reasoning Framework for Video Anomaly Detection and Understanding
Mohd Ubaid Wani, Sara Atito, Josef Kittler +1
Video Anomaly Detection (VAD) aims to temporally localize abnormal events in videos. Most existing approaches rely on dataset-specific training and curated annotations, limiting ge…
From Gaze to Meaning: A Training-Free AI Agent for Unified Grounding and Explanation
Shayan Nasiriboukani, Sara Atito, Mohammad Nezamipour +1
Understanding human attention is fundamental for scene interpretation, yet existing approaches often rely on heavily trained models that lack interpretability. Prior methods strugg…
MorphUNet: Alpha-Controlled Biometric Transport for Diffusion-Based Face Morphing Attacks
Taimoor Rizwan, Sara Atito, Zhenhua Feng +2
Face morphing attacks create synthetic images verifiable against multiple identities, threatening border control and identity verification systems. We introduce MorphUNet, a diffus…
Diff-ID: Identity Consistent Facial Image Generation and Morphing via Diffusion Models
Taimoor Rizwan, Sara Atito, Muhammad Awais +2
Generative diffusion models have revolutionized facial image synthesis, yet robust identity preservation in high resolution outputs remains a critical challenge. This issue is espe…
The Hidden Evolution of Disguised Visual Context inside the VLM
Wish Suharitdamrong, Tony Alex, Xiatian Zhu +2
Visual tokens enter Large Language Models (LLMs) as raw, foreign signals. How they are transformed into meaningful representations and interact with the language space depends enti…
Information theoretic underpinning of self-supervised learning by clustering
Josef Kittler, Sara Atito, Muhammad Awais
Self-supervised learning (SSL) is recognized as an essential tool for building foundation models for Artificial Intelligence applications. The advances in SSL have been made thanks…
Channel-Aware Probing for Multi-Channel Imaging
Umar Marikkar, Syed Sameed Husain, Muhammad Awais +1
Training and evaluating vision encoders on Multi-Channel Imaging (MCI) data remains challenging as channel configurations vary across datasets, preventing fixed-channel training an…
MAGIC-Talk: Motion-aware Audio-Driven Talking Face Generation with Customizable Identity Control
Fatemeh Nazarieh, Zhenhua Feng, Diptesh Kanojia +2
Audio-driven talking face generation has gained significant attention for applications in digital media and virtual avatars. While recent methods improve audio-lip synchronization,…
Dual-Stage Value-Guided Inference with Margin-Based Reward Adjustment for Fast and Faithful VLM Captioning
Ankan Deria, Adinath Madhavrao Dukre, Feilong Tang +5
Despite significant advances in inference-time search for vision-language models (VLMs), existing approaches remain both computationally expensive and prone to unpenalized, low-con…
C3R: Channel Conditioned Cell Representations for unified evaluation in microscopy imaging
Umar Marikkar, Syed Sameed Husain, Muhammad Awais +1
Immunohistochemical (IHC) images reveal detailed information about structures and functions at the subcellular level. However, unlike natural images, IHC datasets pose challenges f…
One Model for ALL: Low-Level Task Interaction Is a Key to Task-Agnostic Image Fusion
Chunyang Cheng, Tianyang Xu, Zhenhua Feng +7
Advanced image fusion methods mostly prioritise high-level missions, where task interaction struggles with semantic gaps, requiring complex bridging mechanisms. In contrast, we pro…
PortraitTalk: Towards Customizable One-Shot Audio-to-Talking Face Generation
Fatemeh Nazarieh, Zhenhua Feng, Diptesh Kanojia +2
Audio-driven talking face generation is a challenging task in digital communication. Despite significant progress in the area, most existing methods concentrate on audio-lip synchr…
Rethinking Positive Pairs in Contrastive Learning
Jiantao Wu, Sara Atito, Zhenhua Feng +3
The training methods in AI do involve semantically distinct pairs of samples. However, their role typically is to enhance the between class separability. The actual notion of simil…
Probabilistically Aligned View-unaligned Clustering with Adaptive Template Selection
Wenhua Dong, Xiao-Jun Wu, Zhenhua Feng +3
In most existing multi-view modeling scenarios, cross-view correspondence (CVC) between instances of the same target from different views, like paired image-text data, is a crucial…
C2C: Component-to-Composition Learning for Zero-Shot Compositional Action Recognition
Rongchang Li, Zhenhua Feng, Tianyang Xu +5
Compositional actions consist of dynamic (verbs) and static (objects) concepts. Humans can easily recognize unseen compositions using the learned concepts. For machines, solving su…
Investigating Self-Supervised Methods for Label-Efficient Learning
Srinivasa Rao Nandam, Sara Atito, Zhenhua Feng +2
Vision transformers combined with self-supervised learning have enabled the development of models which scale across large datasets for several downstream tasks like classification…
Pseudo Labelling for Enhanced Masked Autoencoders
Srinivasa Rao Nandam, Sara Atito, Zhenhua Feng +2
Masked Image Modeling (MIM)-based models, such as SdAE, CAE, GreenMIM, and MixAE, have explored different strategies to enhance the performance of Masked Autoencoders (MAE) by modi…
DailyMAE: Towards Pretraining Masked Autoencoders in One Day
Jiantao Wu, Shentong Mo, Sara Atito +3
Recently, masked image modeling (MIM), an important self-supervised learning (SSL) method, has drawn attention for its effectiveness in learning data representation from unlabeled…
DiCoM -- Diverse Concept Modeling towards Enhancing Generalizability in Chest X-Ray Studies
Abhijeet Parida, Daniel Capellan-Martin, Sara Atito +4
Chest X-Ray (CXR) is a widely used clinical imaging modality and has a pivotal role in the diagnosis and prognosis of various lung and heart related conditions. Conventional automa…
Beyond Accuracy: Statistical Measures and Benchmark for Evaluation of Representation from Self-Supervised Learning
Jiantao Wu, Shentong Mo, Sara Atito +3
Recently, self-supervised metric learning has raised attention for the potential to learn a generic distance function. It overcomes the limitations of conventional supervised one,…
Variantional autoencoder with decremental information bottleneck for disentanglement
Jiantao Wu, Shentong Mo, Xiang Yang +4
One major challenge of disentanglement learning with variational autoencoders is the trade-off between disentanglement and reconstruction fidelity. Previous studies, which increase…