106 citations · 328 across the 22 of their papers we have counts for
23 papers
Spectrum Matching: a Unified Perspective for Superior Diffusability in Latent Diffusion
Mang Ning, Mingxiao Li, Le Zhang +4
In this paper, we study the diffusability (learnability) of variational autoencoders (VAEs) in latent diffusion. We first derive distribution-free bounds on the maximum achievable…
DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Space
Mang Ning, Mingxiao Li, Jianlin Su +6
This paper explores image modeling from the frequency space and introduces DCTdiff, an end-to-end diffusion generative paradigm that efficiently models images in the discrete cosin…
Representation Learning and Identity Adversarial Training for Facial Behavior Understanding
Mang Ning, Albert Ali Salah, Itir Onal Ertugrul
Facial Action Unit (AU) detection has gained significant attention as it enables the breakdown of complex facial expressions into individual muscle movements. In this paper, we rev…
Snakes and Ladders: Two Steps Up for VideoMamba
Hui Lu, Albert Ali Salah, Ronald Poppe
Video understanding requires the extraction of rich spatio-temporal representations, which transformer models achieve through self-attention. Unfortunately, self-attention poses a…
Combining Twitter and Mobile Phone Data to Observe Border-Rush: The Turkish-European Border Opening
Carlos Arcila Calderón, Bilgeçağ Aydoğdu, Tuba Bircan +4
Following Turkey's 2020 decision to revoke border controls, many individuals journeyed towards the Greek, Bulgarian, and Turkish borders. However, the lack of verifiable statistics…
Enhancing Video Transformers for Action Understanding with VLM-aided Training
Hui Lu, Hu Jian, Ronald Poppe +1
Owing to their ability to extract relevant spatio-temporal video embeddings, Vision Transformers (ViTs) are currently the best performing models in video action understanding. Howe…
TCNet: Continuous Sign Language Recognition from Trajectories and Correlated Regions
Hui Lu, Albert Ali Salah, Ronald Poppe
A key challenge in continuous sign language recognition (CSLR) is to efficiently capture long-range spatial interactions over time from the video input. To address this challenge,…
Wrist movement classification for adaptive mobile phone based rehabilitation of children with motor skill impairments
Kayleigh Schoorl, Tamara Pinos Cisneros, Albert Ali Salah +1
Rehabilitation exercises performed by children with cerebral palsy are tedious and repetitive. To make them more engaging, we propose to use an exergame approach, where an adaptive…
Compensation Sampling for Improved Convergence in Diffusion Models
Hui Lu, Albert ali Salah, Ronald Poppe
Diffusion models achieve remarkable quality in image generation, but at a cost. Iterative denoising requires many time steps to produce high fidelity images. We argue that the deno…
Elucidating the Exposure Bias in Diffusion Models
Mang Ning, Mingxiao Li, Jianlin Su +2
Diffusion models have demonstrated impressive generative capabilities, but their \textit{exposure bias} problem, described as the input mismatch between training and sampling, lack…
Fully-attentive and interpretable: vision and video vision transformers for pain detection
Giacomo Fiorentini, Itir Onal Ertugrul, Albert Ali Salah
Pain is a serious and costly issue globally, but to be treated, it must first be detected. Vision transformers are a top-performing architecture in computer vision, with little res…
Automatic Analysis of Human Body Representations in Western Art
Shu Zhao, Almıla Akdağ Salah, Albert Ali Salah
The way the human body is depicted in classical and modern paintings is relevant for art historical analyses. Each artist has certain themes and concerns, resulting in different po…
Video-based estimation of pain indicators in dogs
Hongyi Zhu, Yasemin Salgırlı, Pınar Can +2
Dog owners are typically capable of recognizing behavioral cues that reveal subjective states of their dogs, such as pain. But automatic recognition of the pain state is very chall…
State of the Art of Audio- and Video-Based Solutions for AAL
Slavisa Aleksic, Michael Atanasov, Jean Calleja Agius +36
The report illustrates the state of the art of the most successful AAL applications and functions based on audio and video data, namely (i) lifelogging and self-monitoring, (ii) re…
Going Deeper than Tracking: a Survey of Computer-Vision Based Recognition of Animal Pain and Affective States
Sofia Broomé, Marcelo Feighelstein, Anna Zamansky +6
Advances in animal motion tracking and pose recognition have been a game changer in the study of animal behavior. Recently, an increasing number of works go 'deeper' than tracking,…
Federated learning for violence incident prediction in a simulated cross-institutional psychiatric setting
Thomas Borger, Pablo Mosteiro, Heysem Kaya +4
Inpatient violence is a common and severe problem within psychiatry. Knowing who might become violent can influence staffing levels and mitigate severity. Predictive machine learni…
Speech Analysis for Automatic Mania Assessment in Bipolar Disorder
Pınar Baki, Heysem Kaya, Elvan Çiftçi +2
Bipolar disorder is a mental disorder that causes periods of manic and depressive episodes. In this work, we classify recordings from Bipolar Disorder corpus that contain 7 differe…
Benchmarking Quality-Dependent and Cost-Sensitive Score-Level Multimodal Biometric Fusion Algorithms
Norman Poh, Thirimachos Bourlai, Josef Kittler +13
Automatically verifying the identity of a person by means of biometrics is an important application in day-to-day activities such as accessing banking services and security control…
Is Everything Fine, Grandma? Acoustic and Linguistic Modeling for Robust Elderly Speech Emotion Recognition
Gizem Soğancıoğlu, Oxana Verkholyak, Heysem Kaya +4
Acoustic and linguistic analysis for elderly emotion recognition is an under-studied and challenging research direction, but essential for the creation of digital assistants for th…
Mobile phone data and COVID-19: Missing an opportunity?
Nuria Oliver, Emmanuel Letouzé, Harald Sterly +21
This paper describes how mobile phone data can guide government and public health authorities in determining the best course of action to control the COVID-19 pandemic and in asses…
Data for Refugees: The D4R Challenge on Mobility of Syrian Refugees in Turkey
Albert Ali Salah, Alex Pentland, Bruno Lepri +5
The Data for Refugees (D4R) Challenge is a non-profit challenge initiated to improve the conditions of the Syrian refugees in Turkey by providing a special database to scientific c…
Explaining First Impressions: Modeling, Recognizing, and Explaining Apparent Personality from Videos
Hugo Jair Escalante, Heysem Kaya, Albert Ali Salah +14
Explainability and interpretability are two critical aspects of decision support systems. Within computer vision, they are critical in certain tasks related to human behavior analy…
Adaptive Mixtures of Factor Analyzers
Heysem Kaya, Albert Ali Salah
A mixture of factor analyzers is a semi-parametric density estimator that generalizes the well-known mixtures of Gaussians model by allowing each Gaussian in the mixture to be repr…