5 citations · 8 across the 9 of their papers we have counts for
12 papers
Spatially-Grounded Flow Matching: Structured Source Distributions for Image Generation
Arman Zarei, Mahdi M. Kalayeh
Current flow matching models learn to transport the source i.i.d. Gaussian noise into the target distribution of natural images, yet this source distribution carries no notion of s…
CultureScore: Evaluating Cultural Faithfulness in Video Generation Models
Anku Rani, Wei Dai, Shravan Nayak +3
As video generation models like Veo 3.1 and LTX-2 advance, their ability to accurately represent diverse global cultures remains a critical yet understudied frontier. Current metri…
Envisioning the Future, One Step at a Time
Stefan Andreas Baumann, Jannik Wiese, Tommaso Martorella +2
Accurately anticipating how complex, diverse scenes will evolve requires models that represent uncertainty, simulate along extended interaction chains, and efficiently explore many…
Seeing Sound: Assembling Sounds from Visuals for Audio-to-Image Generation
Darius Petermann, Mahdi M. Kalayeh
Training audio-to-image generative models requires an abundance of diverse audio-visual pairs that are semantically aligned. Such data is almost always curated from in-the-wild vid…
Looking Similar, Sounding Different: Leveraging Counterfactual Cross-Modal Pairs for Audiovisual Representation Learning
Nikhil Singh, Chih-Wei Wu, Iroro Orife +1
Audiovisual representation learning typically relies on the correspondence between sight and sound. However, there are often multiple audio tracks that can correspond with a visual…
On Negative Sampling for Audio-Visual Contrastive Learning from Movies
Mahdi M. Kalayeh, Shervin Ardeshir, Lingyi Liu +2
The abundance and ease of utilizing sound, along with the fact that auditory clues reveal a plethora of information about what happens in a scene, make the audio-visual space an in…
Watching Too Much Television is Good: Self-Supervised Audio-Visual Representation Learning from Movies and TV Shows
Mahdi M. Kalayeh, Nagendra Kamath, Lingyi Liu +1
The abundance and ease of utilizing sound, along with the fact that auditory clues reveal so much about what happens in the scene, make the audio-visual space a perfectly intuitive…
On Symbiosis of Attribute Prediction and Semantic Segmentation
Mahdi M. Kalayeh, Mubarak Shah
In this paper, we propose to employ semantic segmentation to improve person-related attribute prediction. The core idea lies in the fact that the probability of an attribute to app…
Training Faster by Separating Modes of Variation in Batch-normalized Models
Mahdi M. Kalayeh, Mubarak Shah
Batch Normalization (BN) is essential to effectively train state-of-the-art deep Convolutional Neural Networks (CNN). It normalizes inputs to the layers during training using the s…
Human Semantic Parsing for Person Re-identification
Mahdi M. Kalayeh, Emrah Basaran, Muhittin Gokmen +2
Person re-identification is a challenging task mainly due to factors such as background clutter, pose, illumination and camera point of view variations. These elements hinder the p…
Improving Facial Attribute Prediction using Semantic Segmentation
Mahdi M. Kalayeh, Boqing Gong, Mubarak Shah
Attributes are semantically meaningful characteristics whose applicability widely crosses category boundaries. They are particularly important in describing and recognizing concept…
Understanding Trajectory Behavior: A Motion Pattern Approach
Mahdi M. Kalayeh, Stephen Mussmann, Alla Petrakova +2
Mining the underlying patterns in gigantic and complex data is of great importance to data analysts. In this paper, we propose a motion pattern approach to mine frequent behaviors…