891 citations · 1.1k across the 27 of their papers we have counts for
30 papers
TreeSRNF: Square-Root Normal Fields for Generative Modelling of the Geometric and Structural Variability in Tree-like 3D Objects
Tahmina Khanam, Hamid Laga, Mohammed Bennamoun +4
We introduce a novel mathematical framework for analyzing and generating complex tree-shaped 3D objects, such as botanical trees and plants, which deform both in their 3D geometry…
When Rewards Disagree: Reward Weighting for Token-Efficient Video Reasoning
Zinuo Li, Yongxin Guo, Jun Liu +7
Human perception interprets video dynamics by constructing structured mental representations of entities, actions, and temporal boundaries before engaging in high-level reasoning.…
Fact or Fake? Assessing the Role of Deepfake Detectors in Multimodal Misinformation Detection
A S M Sharifuzzaman Sagar, Mohammed Bennamoun, Farid Boussaid +4
In multimodal misinformation, deception usually arises not just from pixel-level manipulations in an image, but from the semantic and contextual claim jointly expressed by the imag…
DynaPURLS: Dynamic Refinement of Part-Aware Representations for Skeleton-Based Zero-Shot Action Recognition
Jingmin Zhu, Anqi Zhu, James Bailey +5
Zero-shot skeleton-based action recognition (ZS-SAR) is fundamentally constrained by prevailing approaches that rely on aligning skeleton features with static, class-level semantic…
Hybrid Transformer-Mamba for Weakly Supervised Volumetric Medical Segmentation
Yiheng Lyu, Lian Xu, Coen Arrow +3
Weakly supervised segmentation enables model training from plane-level labels. Existing methods often rely on 2D encoders, neglecting the volumetric nature of medical data. We prop…
A Riemannian Framework for the Elastic Analysis of the Spatiotemporal Variability in the Shape and Structure of Tree-like 4D Objects
Tahmina Khanam, Hamid Laga, Mohammed Bennamoun +5
This paper introduces a novel computational framework for modeling and analyzing the spatiotemporal shape variability of tree-like 4D structures whose shapes deform and evolve over…
LatentMove: Towards Complex Human Movement Video Generation
Ashkan Taghipour, Morteza Ghahremani, Mohammed Bennamoun +5
Image-to-video (I2V) generation seeks to produce realistic motion sequences from a single reference image. Although recent methods exhibit strong temporal consistency, they often s…
Watch and Listen: Understanding Audio-Visual-Speech Moments with Multimodal LLM
Zinuo Li, Xian Zhang, Yongxin Guo +5
Humans naturally understand moments in a video by integrating visual and auditory cues. For example, localizing a scene in the video like "A scientist passionately speaks on wildli…
Dynamic Neural Surfaces for Elastic 4D Shape Representation and Analysis
Awais Nizamani, Hamid Laga, Guanjin Wang +3
We propose a novel framework for the statistical analysis of genus-zero 4D surfaces, i.e., 3D surfaces that deform and evolve over time. This problem is particularly challenging du…
UIFormer: A Unified Transformer-based Framework for Incremental Few-Shot Object Detection and Instance Segmentation
Chengyuan Zhang, Yilin Zhang, Lei Zhu +6
This paper introduces a novel framework for unified incremental few-shot object detection (iFSOD) and instance segmentation (iFSIS) using the Transformer architecture. Our goal is…
A Riemannian Approach for Spatiotemporal Analysis and Generation of 4D Tree-shaped Structures
Tahmina Khanam, Hamid Laga, Mohammed Bennamoun +5
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, an…
Faster Image2Video Generation: A Closer Look at CLIP Image Embedding's Impact on Spatio-Temporal Cross-Attentions
Ashkan Taghipour, Morteza Ghahremani, Mohammed Bennamoun +4
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…
Auxiliary Tasks Enhanced Dual-affinity Learning for Weakly Supervised Semantic Segmentation
Lian Xu, Mohammed Bennamoun, Farid Boussaid +3
Most existing weakly supervised semantic segmentation (WSSS) methods rely on Class Activation Mapping (CAM) to extract coarse class-specific localization maps using image-level lab…
Box It to Bind It: Unified Layout Control and Attribute Binding in T2I Diffusion Models
Ashkan Taghipour, Morteza Ghahremani, Mohammed Bennamoun +3
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 a…
Transformers in Small Object Detection: A Benchmark and Survey of State-of-the-Art
Aref Miri Rekavandi, Shima Rashidi, Farid Boussaid +3
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…
MCTformer+: Multi-Class Token Transformer for Weakly Supervised Semantic Segmentation
Lian Xu, Mohammed Bennamoun, Farid Boussaid +3
This paper proposes a novel transformer-based framework that aims to enhance weakly supervised semantic segmentation (WSSS) by generating accurate class-specific object localizatio…
3D Brain and Heart Volume Generative Models: A Survey
Yanbin Liu, Girish Dwivedi, Farid Boussaid +1
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 capabil…
Active-Passive SimStereo -- Benchmarking the Cross-Generalization Capabilities of Deep Learning-based Stereo Methods
Laurent Jospin, Allen Antony, Lian Xu +3
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-…
Bayesian Learning for Disparity Map Refinement for Semi-Dense Active Stereo Vision
Laurent Valentin Jospin, Hamid Laga, Farid Boussaid +1
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 e…
A Guide to Image and Video based Small Object Detection using Deep Learning : Case Study of Maritime Surveillance
Aref Miri Rekavandi, Lian Xu, Farid Boussaid +3
Small object detection (SOD) in optical images and videos is a challenging problem that even state-of-the-art generic object detection methods fail to accurately localize and ident…
Learning Resolution-Adaptive Representations for Cross-Resolution Person Re-Identification
Lin Wu, Lingqiao Liu, Yang Wang +3
The cross-resolution person re-identification (CRReID) problem aims to match low-resolution (LR) query identity images against high resolution (HR) gallery images. It is a challeng…
Pseudo-Pair based Self-Similarity Learning for Unsupervised Person Re-identification
Lin Wu, Deyin Liu, Wenying Zhang +5
Person re-identification (re-ID) is of great importance to video surveillance systems by estimating the similarity between a pair of cross-camera person shorts. Current methods for…
Jacobian Norm with Selective Input Gradient Regularization for Improved and Interpretable Adversarial Defense
Deyin Liu, Lin Wu, Haifeng Zhao +3
Deep neural networks (DNNs) are known to be vulnerable to adversarial examples that are crafted with imperceptible perturbations, i.e., a small change in an input image can induce…
CrossFormer: Cross Spatio-Temporal Transformer for 3D Human Pose Estimation
Mohammed Hassanin, Abdelwahed Khamiss, Mohammed Bennamoun +2
3D human pose estimation can be handled by encoding the geometric dependencies between the body parts and enforcing the kinematic constraints. Recently, Transformer has been adopte…