790 citations · 1.1k across the 9 of their papers we have counts for
11 papers
SAVU-BENCH: A Real-World Benchmark for Spatial Audio-Visual Understanding
Yu Chen, Ruihang Liu, Yangguang Xu +5
Spatial audio-visual understanding requires models to recognize not only what is present, but also where events occur and how they relate across modalities. Existing benchmarks oft…
NeuralSRNF: Neural Square Root Normal Fields for the Statistical Shape Analysis and Generation of Nonrigid 3D and 4D Objects
Awais Nizamani, Hamid Laga, Guanjin Wang +3
We introduce NeuralSRNF, a novel framework for the statistical shape analysis and generation of genus-zero 3D and 4D objects that undergo nonrigid deformations. Traditional methods…
Learning Structured Visual Compositional Representations for Weakly Supervised Referring Expression Comprehension
Lian Xu, Mohammed Bennamoun, Farid Boussaid +3
Referring expression comprehension (REC) aims to localize the object in an image described by natural language. In Weakly supervised REC (WREC), existing approaches primarily opera…
SkelHCC: A Hyperbolic CLIP-Driven Cache Adaptation Framework for Skeleton-based One-Shot Action Recognition
Yanan Liu, Anqi Zhu, Jingmin Zhu +6
Skeleton-based action recognition aims to understand human behaviors from body joint sequences and is especially challenging in the one-shot setting, where only a single labeled ex…
SkeletonContext: Skeleton-side Context Prompt Learning for Zero-Shot Skeleton-based Action Recognition
Ning Wang, Tieyue Wu, Naeha Sharif +5
Zero-shot skeleton-based action recognition aims to recognize unseen actions by transferring knowledge from seen categories through semantic descriptions. Most existing methods typ…
Controllable Complex Human Motion Video Generation via Text-to-Skeleton Cascades
Ashkan Taghipour, Morteza Ghahremani, Zinuo Li +3
Generating videos of complex human motions such as flips, cartwheels, and martial arts remains challenging for current video diffusion models. Text-only conditioning is temporally…
A Survey on Deep Learning Techniques for Stereo-based Depth Estimation
Hamid Laga, Laurent Valentin Jospin, Farid Boussaid +1
Estimating depth from RGB images is a long-standing ill-posed problem, which has been explored for decades by the computer vision, graphics, and machine learning communities. Among…
Exploiting Layerwise Convexity of Rectifier Networks with Sign Constrained Weights
Senjian An, Farid Boussaid, Mohammed Bennamoun +1
By introducing sign constraints on the weights, this paper proposes sign constrained rectifier networks (SCRNs), whose training can be solved efficiently by the well known majoriza…
On the Compressive Power of Deep Rectifier Networks for High Resolution Representation of Class Boundaries
Senjian An, Mohammed Bennamoun, Farid Boussaid
This paper provides a theoretical justification of the superior classification performance of deep rectifier networks over shallow rectifier networks from the geometrical perspecti…
From Deep to Shallow: Transformations of Deep Rectifier Networks
Senjian An, Farid Boussaid, Mohammed Bennamoun +1
In this paper, we introduce transformations of deep rectifier networks, enabling the conversion of deep rectifier networks into shallow rectifier networks. We subsequently prove th…
A New Representation of Skeleton Sequences for 3D Action Recognition
Qiuhong Ke, Mohammed Bennamoun, Senjian An +2
This paper presents a new method for 3D action recognition with skeleton sequences (i.e., 3D trajectories of human skeleton joints). The proposed method first transforms each skele…