Related papers: Self-Paced Neutral Expression-Disentangled Learnin…

Unified image restoration models for diverse and mixed degradations often suffer from unstable optimization dynamics and inter-task conflicts. This paper introduces Self-Improved Privilege Learning (SIPL), a novel paradigm that overcomes…

Motivated by the following two observations: 1) people are aging differently under different conditions for changeable facial attributes, e.g., skin color may become darker when working outside, and 2) it needs to keep some unchanged facial…

Person re-identification (Re-ID) usually suffers from noisy samples with background clutter and mutual occlusion, which makes it extremely difficult to distinguish different individuals across the disjoint camera views. In this paper, we…

Federated Learning (FL) is a paradigm for large-scale distributed learning which faces two key challenges: (i) efficient training from highly heterogeneous user data, and (ii) protecting the privacy of participating users. In this work, we…

The large pose discrepancy between two face images is one of the fundamental challenges in automatic face recognition. Conventional approaches to pose-invariant face recognition either perform face frontalization on, or learn a…

Scalable 6D pose estimation for rigid objects from RGB images aims at handling multiple objects and generalizing to novel objects. Building on a well-known auto-encoding framework to cope with object symmetry and the lack of labeled…

Facial expressions are one of the most powerful ways for depicting specific patterns in human behavior and describing human emotional state. Despite the impressive advances of affective computing over the last decade, automatic video-based…

Facial expressions vary from person to person, and the brightness, contrast, and resolution of every random image are different. This is why recognizing facial expressions is very difficult. This article proposes an efficient system for…

Facial optical flow supports a wide range of tasks in facial motion analysis. However, the lack of high-resolution facial optical flow datasets has hindered progress in this area. In this paper, we introduce Splatting Rasterization Flow…

Deep facial expression recognition faces two challenges that both stem from the large number of trainable parameters: long training times and a lack of interpretability. We propose a novel method based on evolutionary algorithms, that deals…

Face Presentation Attack Detection (PAD) demands incremental learning (IL) to combat evolving spoofing tactics and domains. Privacy regulations, however, forbid retaining past data, necessitating rehearsal-free IL (RF-IL). Vision-Language…

The goal of this work is to develop self-sufficient framework for Continuous Sign Language Recognition (CSLR) that addresses key issues of sign language recognition. These include the need for complex multi-scale features such as hands,…

Image and video-capturing technologies have permeated our every-day life. Such technologies can continuously monitor individuals' expressions in real-life settings, affording us new insights into their emotional states and transitions, thus…

Disentangled representations have recently been shown to improve fairness, data efficiency and generalisation in simple supervised and reinforcement learning tasks. To extend the benefits of disentangled representations to more complex…

Cross-modal retrieval is crucial in understanding latent correspondences across modalities. However, existing methods implicitly assume well-matched training data, which is impractical as real-world data inevitably involves imperfect…

One-shot video-driven talking face generation aims at producing a synthetic talking video by transferring the facial motion from a video to an arbitrary portrait image. Head pose and facial expression are always entangled in facial motion…

Heterogeneous face matching is a challenge issue in face recognition due to large domain difference as well as insufficient pairwise images in different modalities during training. This paper proposes a coupled deep learning (CDL) approach…

Pain management and severity detection are crucial for effective treatment, yet traditional self-reporting methods are subjective and may be unsuitable for non-verbal individuals (people with limited speaking skills). To address this…

Deep Reinforcement Learning (DRL) has been a promising solution to many complex decision-making problems. Nevertheless, the notorious weakness in generalization among environments prevent widespread application of DRL agents in real-world…

Ophthalmologists typically require multimodal data sources to improve diagnostic accuracy in clinical decisions. However, due to medical device shortages, low-quality data and data privacy concerns, missing data modalities are common in…