← Search

Farid Boussaid

16 accepted papers

2026

SkelHCC: A Hyperbolic CLIP-Driven Cache Adaptation Framework for Skeleton-based One-Shot Action Recognition

ICML 2026poster

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 exemplar is available for each novel action. A key challenge is learning representations that capture the hierarchical and…

Cited by 0SourceScholar
2026

SkeletonContext: Skeleton-side Context Prompt Learning for Zero-Shot Skeleton-based Action Recognition

CVPR 2026

Zero-shot skeleton-based action recognition aims to recognize unseen actions by transferring knowledge from seen categories through semantic descriptions. Most existing methods typically align skeleton features with textual embeddings within a shared latent space. However, the absence of contextual

Cited by 0SourcecodeScholar
2025

Dynamic Neural Surfaces for Elastic 4D Shape Representation and Analysis

CVPR 2025poster

We propose a novel framework for the statistical analysis of genus-zero 4D surfaces, i.e., 3D surfaces that deform and evolve overtime. This problem is particularly challenging due to the arbitrary parameterizations of these surfaces and their varying deformation speeds, necessitating effective spat…

Cited by 0SourcePDFScholar
2025

Watch and Listen: Understanding Audio-Visual-Speech Moments with Multimodal LLM

NeurIPS 2025poster

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 wildlife conservation as dramatic orchestral music plays, with the audience nodding and applauding” requires simultaneous proc…

Cited by 0SourceScholar
2024

A Riemannian Approach for Spatiotemporal Analysis and Generation of 4D Tree-shaped Structures

ECCV 2024oral

"We propose the first comprehensive approach for modeling and analyzing the spatiotemporal shape variability in tree-like 4D objects, 3D objects whose shapes bend, stretch and change in their branching structure over time as they deform, grow, and interact with their environment. Our key contributio…

2024

AEDNet: Adaptive Embedding and Multiview-Aware Disentanglement for Point Cloud Completion

ECCV 2024poster

"Point cloud completion involves inferring missing parts of 3D objects from incomplete point cloud data. It requires a model that understands the global structure of the object and reconstructs local details. To this end, we propose a global perception and local attention network, termed AEDNet, for…

Cited by 1SourcePDFScholar
2023

Learning Multi-Modal Class-Specific Tokens for Weakly Supervised Dense Object Localization

CVPR 2023poster

Weakly supervised dense object localization (WSDOL) relies generally on Class Activation Mapping (CAM), which exploits the correlation between the class weights of the image classifier and the pixel-level features. Due to the limited ability to address intra-class variations, the image classifier ca…

2023

Reinforced Learning for Label-Efficient 3D Face Reconstruction

ICRA 2023poster

3D face reconstruction plays a major role in many human-robot interaction systems, from automatic face authentication to human-computer interface-based entertainment. To improve robustness against occlusions and noise, 3D face reconstruction networks are often trained on a set of in-the-wild face im…

Cited by 1SourceScholar
2023

VAPCNet: Viewpoint-Aware 3D Point Cloud Completion

ICCV 2023poster

Most existing learning-based 3D point cloud completion methods ignore the fact that the completion process is highly coupled with the viewpoint of a partial scan. However, the various viewpoints of incompletely scanned objects in real-world applications are normally unknown and directly estimating t…

Cited by 12PDFcodeScholar
2022

Active-Passive SimStereo - Benchmarking the Cross-Generalization Capabilities of Deep Learning-based Stereo Methods

NeurIPS 2022accept

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 identified without ambiguity. However, the projec…

Cited by 4SourcePDFScholar
2022

Multi-Class Token Transformer for Weakly Supervised Semantic Segmentation

CVPR 2022poster

This paper proposes a new transformer-based framework to learn class-specific object localization maps as pseudo labels for weakly supervised semantic segmentation (WSSS). Inspired by the fact that the attended regions of the one-class token in the standard vision transformer can be leveraged to for…

Cited by 301PDFcodeScholar
2021

Leveraging Auxiliary Tasks With Affinity Learning for Weakly Supervised Semantic Segmentation

ICCV 2021poster

Semantic segmentation is a challenging task in the absence of densely labelled data. Only relying on class activation maps (CAM) with image-level labels provides deficient segmentation supervision. Prior works thus consider pre-trained models to produce coarse saliency maps to guide the generation o…

Cited by 154PDFcodeScholar
2017

A New Representation of Skeleton Sequences for 3D Action Recognition

CVPR 2017poster

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 skeleton sequence into three clips each consisting of several frames for spatial temporal feature learning using deep neural…

Cited by 1080PDFScholar
2015

Contractive Rectifier Networks for Nonlinear Maximum Margin Classification

ICCV 2015poster

To find the optimal nonlinear separating boundary with maximum margin in the input data space, this paper proposes Contractive Rectifier Networks (CRNs), wherein the hidden-layer transformations are restricted to be contraction mappings. The contractive constraints ensure that the achieved separatin…

Cited by 13PDFScholar
2015

How Can Deep Rectifier Networks Achieve Linear Separability and Preserve Distances?

ICML 2015poster

This paper investigates how hidden layers of deep rectifier networks are capable of transforming two or more pattern sets to be linearly separable while preserving the distances with a guaranteed degree, and proves the universal classification power of such distance preserving rectifier networks. Th…

Cited by 34SourcePDFScholar