Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Pascal FuaSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works358 from public data
- Context-Aware Crowd Counting735
This paper introduces an end-to-end trainable deep architecture that combines features obtained using multiple receptive field sizes and learns the importance of each such feature at each image location, which yields an algorithm that outperforms state-of-the-art crowd counting methods, especially when perspective effects are strong.
- Learning Trajectory Dependencies for Human Motion Prediction584
A simple feed-forward deep network for motion prediction, which takes into account both temporal smoothness and spatial dependencies among human body joints, and design a new graph convolutional network to learn graph connectivity automatically.
- Learning to Find Good Correspondences551
A novel normalization technique, called Context Normalization, is introduced, which allows the network to process each data point separately while embedding global information in it, and also makes the network invariant to the order of the correspondences.
- Beyond Sharing Weights for Deep Domain Adaptation479
This work introduces a two-stream architecture, where one operates in the source domain and the other in the target domain, and demonstrates that this both yields higher accuracy than state-of-the-art methods on several object recognition and detection tasks and consistently outperforms networks with shared weights in both supervised and unsupervised settings.
- 463
- Evaluating The Search Phase of Neural Architecture Search383
This paper finds that on average, the state-of-the-art NAS algorithms perform similarly to the random policy; the widely-used weight sharing strategy degrades the ranking of the NAS candidates to the point of not reflecting their true performance, thus reducing the effectiveness of the search process.
- 382
- History Repeats Itself: Human Motion Prediction via Motion Attention381
An attention-based feed-forward network is introduced that explicitly leverages the observation that human motion tends to repeat itself to capture motion attention to capture the similarity between the current motion context and the historical motion sub-sequences.
- Segmentation-Driven 6D Object Pose Estimation329
This paper introduces a segmentation-driven 6D pose estimation framework where each visible part of the objects contributes a local pose prediction in the form of 2D keypoint locations and uses a predicted measure of confidence to combine these pose candidates into a robust set of 3D-to-2D correspondences.
- Kernel Methods on the Riemannian Manifold of Symmetric Positive Definite Matrices316
To encode the geometry of the manifold in the mapping, a family of provably positive definite kernels on the Riemannian manifold of SPD matrices is introduced, derived from the Gaussian kernel, but exploit different metrics on the manifold.
- Structured Prediction of 3D Human Pose with Deep Neural Networks282
This paper introduces a Deep Learning regression architecture for structured prediction of 3D human pose from monocular images that relies on an overcomplete autoencoder to learn a high-dimensional latent pose representation and account for joint dependencies.
- Kernel Methods on Riemannian Manifolds with Gaussian RBF Kernels270
It is shown that many popular algorithms designed for Euclidean spaces, such as support vector machines, discriminant analysis and principal component analysis can be generalized to Riemannian manifolds with the help of such positive definite Gaussian kernels.
- Learning Monocular 3D Human Pose Estimation from Multi-view Images265
This paper trains the system to predict the same pose in all views, and proposes a method to estimate camera pose jointly with human pose, which lets us utilize multiview footage where calibration is difficult, e.g., for pan-tilt or moving handheld cameras.
- Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation262
A novel architecture designed to deliver the best of both worlds by performing both simultaneously and fusing the information along the way and yields significant improvements upon the state-of-the-art on standard 3D human pose estimation benchmarks.
- Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation242
This paper proposes a geometry-aware body representation from multi-view images without annotations that significantly outperforms fully-supervised methods given the same amount of labeled data, and improves over other semi-super supervised methods while using as little as 1% of the labeled data.
- Detecting the Unexpected via Image Resynthesis235
This paper tackles the more realistic scenario where unexpected objects of unknown classes can appear at test time and translates the problem of detecting unknown classes to one of identifying poorly-resynthesized image regions, which outperforms both uncertainty- and autoencoder-based methods.
- Dimensionality Reduction on SPD Manifolds: The Emergence of Geometry-Aware Methods228
This paper proposes to model the mapping from the high-dimensional SPD manifold to the low-dimensional one with an orthonormal projection and shows that learning can be expressed as an optimization problem on a Grassmann manifold and discusses fast solutions for special cases.
- Single-Stage 6D Object Pose Estimation227
This work introduces a deep architecture that directly regresses 6D poses from correspondences and can be exploited in conjunction with existing correspondence-extraction networks so as to yield single-stage 6D pose estimation frameworks.
- From Manifold to Manifold: Geometry-Aware Dimensionality Reduction for SPD Matrices214
An approach that lets us handle high-dimensional SPD matrices by constructing a lower-dimensional, more discriminative SPD manifold is introduced and leads to a significant accuracy gain over state-of-the-art methods.
- Factorized Latent Spaces with Structured Sparsity206
This paper shows that structured sparsity allows us to address the multi-view learning problem by alternately solving two convex optimization problems and shows that the resulting factorized latent spaces generalize over existing approaches in that they allow having latent dimensions shared between any subset of the views instead of between all the views only.
- 204
- Encouraging LSTMs to Anticipate Actions Very Early184
A new action anticipation method that achieves high prediction accuracy even in the presence of a very small percentage of a video sequence, and develops a multi-stage LSTM architecture that leverages context-aware and action-aware features, and introduces a novel loss function that encourages the model to predict the correct class as early as possible.
- GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence179
GigaPose first leverages discriminative “templates ”, ren-dered images of the CAD models, to recover the out-of-plane rotation and then uses patch correspondences to estimate the four remaining parameters, resulting in a speedup factor of 35x compared to the state of the art.
- CLIP the Gap: A Single Domain Generalization Approach for Object Detection169
This work proposes to leverage a pre-trained vision-language model to introduce semantic domain concepts via textual prompts to address the challenges of simultaneously learning robust object localization and representation, and outperforms the only existing SDG object detection method, Single-DGOD.
- Effective Use of Synthetic Data for Urban Scene Semantic Segmentation164
A drastically different way to handle synthetic images that does not require seeing any real images at training time is introduced, which builds on the observation that foreground and background classes are not affected in the same manner by the domain shift, and thus should be treated differently.
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.