Related papers: MA-ViT: Modality-Agnostic Vision Transformers for …
Multimodal Face Anti-Spoofing (FAS) methods, which integrate multiple visual modalities, often suffer even more severe performance degradation than unimodal FAS when deployed in unseen domains. This is mainly due to two overlooked risks…
The progression of deep learning and the widespread adoption of sensors have facilitated automatic multi-view fusion (MVF) about the cardiovascular system (CVS) signals. However, prevalent MVF model architecture often amalgamates CVS…
As generative artificial intelligence evolves, deepfake attacks have escalated from single-modality manipulations to complex, multimodal threats. Existing forensic techniques face a severe generalization bottleneck: by relying excessively…
We present a simplified, task-agnostic multi-modal pre-training approach that can accept either video or text input, or both for a variety of end tasks. Existing pre-training are task-specific by adopting either a single cross-modal encoder…
Modern multi-object tracking (MOT) system usually involves separated modules, such as motion model for location and appearance model for data association. However, the compatible problems within both motion and appearance models are always…
Deepfakes have recently raised significant trust issues and security concerns among the public. Compared to CNN face forgery detectors, ViT-based methods take advantage of the expressivity of transformers, achieving superior detection…
Humans possess remarkable ability to accurately classify new, unseen images after being exposed to only a few examples. Such ability stems from their capacity to identify common features shared between new and previously seen images while…
Representation learning for sketch-based image retrieval has mostly been tackled by learning embeddings that discard modality-specific information. As instances from different modalities can often provide complementary information…
The Vision Transformer (ViT) excels in global modeling but faces deployment challenges on resource-constrained devices due to the quadratic computational complexity of its attention mechanism. To address this, we propose the Semantic-Aware…
Deep learning vision systems are increasingly deployed in safety-critical domains such as healthcare, yet they remain vulnerable to small adversarial patches that can trigger misclassifications. Most existing defenses assume a single patch…
We propose Masked-Attention Transformers for Surgical Instrument Segmentation (MATIS), a two-stage, fully transformer-based method that leverages modern pixel-wise attention mechanisms for instrument segmentation. MATIS exploits the…
Holistic methods using CNNs and margin-based losses have dominated research on face recognition. In this work, we depart from this setting in two ways: (a) we employ the Vision Transformer as an architecture for training a very strong…
In the research field of few-shot learning, the main difference between image-based and video-based is the additional temporal dimension. In recent years, some works have used the Transformer to deal with frames, then get the attention…
The vulnerability of face recognition systems to presentation attacks has limited their application in security-critical scenarios. Automatic methods of detecting such malicious attempts are essential for the safe use of facial recognition…
Aiming to advance AI agents, large foundation models significantly improve reasoning and instruction execution, yet the current focus on vision and language neglects the potential of perceiving diverse modalities in open-world environments.…
Vision Transformers (ViTs) have emerged as a foundational model in computer vision, excelling in generalization and adaptation to downstream tasks. However, deploying ViTs to support diverse resource constraints typically requires…
Weakly supervised video anomaly detection (WS-VAD) is to distinguish anomalies from normal events based on discriminative representations. Most existing works are limited in insufficient video representations. In this work, we develop a…
Mitigating biases in computer vision models is an essential step towards the trustworthiness of artificial intelligence models. Existing bias mitigation methods focus on a small set of predefined biases, limiting their applicability in…
Recently, Vision Transformer (ViT) has achieved promising performance in image recognition and gradually serves as a powerful backbone in various vision tasks. To satisfy the sequential input of Transformer, the tail of ViT first splits…
Pose variation is one of the key challenges in face recognition. Conventional techniques mainly focus on face frontalization or face augmentation in image space. However, transforming face images in image space is not guaranteed to preserve…