Related papers: DisenQ: Disentangling Q-Former for Activity-Biomet…
In this work, we study a novel problem which focuses on person identification while performing daily activities. Learning biometric features from RGB videos is challenging due to spatio-temporal complexity and presence of appearance biases…
Multi-behavioral recommender systems have emerged as a solution to address data sparsity and cold-start issues by incorporating auxiliary behaviors alongside target behaviors. However, existing models struggle to accurately capture varying…
Recent successes of deep learning-based recognition rely on maintaining the content related to the main-task label. However, how to explicitly dispel the noisy signals for better generalization in a controllable manner remains an open…
Learning disentangled representations of data is a fundamental problem in artificial intelligence. Specifically, disentangled latent representations allow generative models to control and compose the disentangled factors in the synthesis…
With the rise of cameras and smart sensors, humanity generates an exponential amount of data. This valuable information, including underrepresented cases like AI in medical settings, can fuel new deep-learning tools. However, data…
Human motion data is inherently rich and complex, containing both semantic content and subtle stylistic features that are challenging to model. We propose a novel method for effective disentanglement of the style and content in human motion…
In this paper, we propose a framework for disentangling the appearance and geometry representations in the face recognition task. To provide supervision for this aim, we generate geometrically identical faces by incorporating spatial…
Recognizing human activities in videos is challenging due to the spatio-temporal complexity and context-dependence of human interactions. Prior studies often rely on single input modalities, such as RGB or skeletal data, limiting their…
In wearable-based human activity recognition (HAR) research, one of the major challenges is the large intra-class variability problem. The collected activity signal is often, if not always, coupled with noises or bias caused by personal,…
Learning disentangled representations in sequential data is a key goal in deep learning, with broad applications in vision, audio, and time series. While real-world data involves multiple interacting semantic factors over time, prior work…
Neural shape models can represent complex 3D shapes with a compact latent space. When applied to dynamically deforming shapes such as the human hands, however, they would need to preserve temporal coherence of the deformation as well as the…
Session-based recommendation aims to predict intents of anonymous users based on their limited behaviors. Modeling user behaviors involves two distinct rationales: co-occurrence patterns reflected by item IDs, and fine-grained preferences…
High quality facial image editing is a challenging problem in the movie post-production industry, requiring a high degree of control and identity preservation. Previous works that attempt to tackle this problem may suffer from the…
The deep learning revolution has strongly impacted low-level image processing tasks such as style/domain transfer, enhancement/restoration, and visual quality assessments. Despite often being treated separately, the aforementioned tasks…
Clothes-changing person re-identification (CC-ReID) aims to recognize individuals under different clothing scenarios. Current CC-ReID approaches either concentrate on modeling body shape using additional modalities including silhouette,…
We present X-UniMotion, a unified and expressive implicit latent representation for whole-body human motion, encompassing facial expressions, body poses, and hand gestures. Unlike prior motion transfer methods that rely on explicit skeletal…
In this work, we present a novel approach to multi-view action recognition where we guide learned action representations to be separated from view-relevant information in a video. When trying to classify action instances captured from…
Speech-driven 3D facial animation aims to synthesize vivid facial animations that accurately synchronize with speech and match the unique speaking style. However, existing works primarily focus on achieving precise lip synchronization while…
We present techniques for improving performance driven facial animation, emotion recognition, and facial key-point or landmark prediction using learned identity invariant representations. Established approaches to these problems can work…
Gait, the walking pattern of individuals, is one of the important biometrics modalities. Most of the existing gait recognition methods take silhouettes or articulated body models as gait features. These methods suffer from degraded…