Zobrazeno 1 - 10
of 251
pro vyhledávání: '"Boussaid, Farid"'
Autor:
Khanam, Tahmina, Laga, Hamid, Bennamoun, Mohammed, Wang, Guanjin, Sohel, Ferdous, Boussaid, Farid, Wang, Guan, Srivastava, Anuj
We propose the first comprehensive approach for modeling and analyzing the spatiotemporal shape variability in tree-like 4D objects, i.e., 3D objects whose shapes bend, stretch, and change in their branching structure over time as they deform, grow,
Externí odkaz:
http://arxiv.org/abs/2408.12443
Autor:
Taghipour, Ashkan, Ghahremani, Morteza, Bennamoun, Mohammed, Rekavandi, Aref Miri, Li, Zinuo, Laga, Hamid, Boussaid, Farid
This paper investigates the role of CLIP image embeddings within the Stable Video Diffusion (SVD) framework, focusing on their impact on video generation quality and computational efficiency. Our findings indicate that CLIP embeddings, while crucial
Externí odkaz:
http://arxiv.org/abs/2407.19205
Most existing weakly supervised semantic segmentation (WSSS) methods rely on Class Activation Mapping (CAM) to extract coarse class-specific localization maps using image-level labels. Prior works have commonly used an off-line heuristic thresholding
Externí odkaz:
http://arxiv.org/abs/2403.01156
Autor:
Taghipour, Ashkan, Ghahremani, Morteza, Bennamoun, Mohammed, Rekavandi, Aref Miri, Laga, Hamid, Boussaid, Farid
While latent diffusion models (LDMs) excel at creating imaginative images, they often lack precision in semantic fidelity and spatial control over where objects are generated. To address these deficiencies, we introduce the Box-it-to-Bind-it (B2B) mo
Externí odkaz:
http://arxiv.org/abs/2402.17910
Autor:
Rekavandi, Aref Miri, Rashidi, Shima, Boussaid, Farid, Hoefs, Stephen, Akbas, Emre, bennamoun, Mohammed
Transformers have rapidly gained popularity in computer vision, especially in the field of object recognition and detection. Upon examining the outcomes of state-of-the-art object detection methods, we noticed that transformers consistently outperfor
Externí odkaz:
http://arxiv.org/abs/2309.04902
This paper proposes a novel transformer-based framework that aims to enhance weakly supervised semantic segmentation (WSSS) by generating accurate class-specific object localization maps as pseudo labels. Building upon the observation that the attend
Externí odkaz:
http://arxiv.org/abs/2308.03005
Autor:
Tang, Hao, Rekavandi, Aref Miri, Rooprai, Dharjinder, Dwivedi, Girish, Sanfilippo, Frank, Boussaid, Farid, Bennamoun, Mohammed
This study investigates the effectiveness of Explainable Artificial Intelligence (XAI) techniques in predicting suicide risks and identifying the dominant causes for such behaviours. Data augmentation techniques and ML models are utilized to predict
Externí odkaz:
http://arxiv.org/abs/2303.06052
Generative models such as generative adversarial networks and autoencoders have gained a great deal of attention in the medical field due to their excellent data generation capability. This paper provides a comprehensive survey of generative models f
Externí odkaz:
http://arxiv.org/abs/2210.05952
In stereo vision, self-similar or bland regions can make it difficult to match patches between two images. Active stereo-based methods mitigate this problem by projecting a pseudo-random pattern on the scene so that each patch of an image pair can be
Externí odkaz:
http://arxiv.org/abs/2209.08305
A major focus of recent developments in stereo vision has been on how to obtain accurate dense disparity maps in passive stereo vision. Active vision systems enable more accurate estimations of dense disparity compared to passive stereo. However, sub
Externí odkaz:
http://arxiv.org/abs/2209.05082