Search Results for author:
Found 11 papers, 10 papers with code
Toward Reliable Human Pose Forecasting with Uncertainty
Recently, there has been an arms race of pose forecasting methods aimed at solving the spatio-temporal task of predicting a sequence of future 3D poses of a person given a sequence of past observed ones.
A generic diffusion-based approach for 3D human pose prediction in the wild
Predicting 3D human poses in real-world scenarios, also known as human pose forecasting, is inevitably subject to noisy inputs arising from inaccurate 3D pose estimations and occlusions.
Ranked #1 on
Human Pose Forecasting
on HumanEva-I
Pedestrian Stop and Go Forecasting with Hybrid Feature Fusion
Considering the lack of suitable existing datasets for it, we release TRANS, a benchmark for explicitly studying the stop and go behaviors of pedestrians in urban traffic.
A Shared Representation for Photorealistic Driving Simulators
We build on successful cGAN models to propose a new semantically-aware discriminator that better guides the generator.
Do Pedestrians Pay Attention? Eye Contact Detection in the Wild
In urban or crowded environments, humans rely on eye contact for fast and efficient communication with nearby people.
TTT++: When Does Self-Supervised Test-Time Training Fail or Thrive?
In this work, we first provide an in-depth look at its limitations and show that TTT can possibly deteriorate, instead of improving, the test-time performance in the presence of severe distribution shifts.
Detecting 32 Pedestrian Attributes for Autonomous Vehicles
By increasing the number of attributes jointly learned, we highlight an issue related to the scales of gradients, which arises in MTL with numerous tasks.
MonStereo: When Monocular and Stereo Meet at the Tail of 3D Human Localization
Monocular and stereo visions are cost-effective solutions for 3D human localization in the context of self-driving cars or social robots.
Revisiting Multi-Task Learning with ROCK: a Deep Residual Auxiliary Block for Visual Detection
Multi-Task Learning (MTL) is appealing for deep learning regularization.
Deformable Part-based Fully Convolutional Network for Object Detection
Existing region-based object detectors are limited to regions with fixed box geometry to represent objects, even if those are highly non-rectangular.
WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation
This paper introduces WILDCAT, a deep learning method which jointly aims at aligning image regions for gaining spatial invariance and learning strongly localized features.
Ranked #3 on
Weakly Supervised Object Detection
on MS COCO
