Search Results for author: Alexandre Alahi

Found 104 papers, 65 papers with code

From Generation to Generalization: Emergent Few-Shot Learning in Video Diffusion Models

no code implementations8 Jun 2025 Pablo Acuaviva, Aram Davtyan, Mariam Hassan, Sebastian Stapf, Ahmad Rahimi, Alexandre Alahi, Paolo Favaro

To probe the extent of this internal knowledge, we introduce a few-shot fine-tuning framework that repurposes VDMs for new tasks using only a handful of examples.

ARC Few-Shot Learning +2

VoxDet: Rethinking 3D Semantic Occupancy Prediction as Dense Object Detection

no code implementations5 Jun 2025 Wuyang Li, Zhu Yu, Alexandre Alahi

Building on this, we further propose VoxDet, an instance-centric framework that reformulates the voxel-level occupancy prediction as dense object detection by decoupling it into two sub-tasks: offset regression and semantic prediction.

3D geometry 3D Semantic Occupancy Prediction +2

X-GRM: Large Gaussian Reconstruction Model for Sparse-view X-rays to Computed Tomography

1 code implementation21 May 2025 Yifan Liu, Wuyang Li, Weihao Yu, Chenxin Li, Alexandre Alahi, Max Meng, Yixuan Yuan

Existing CT reconstruction works are limited to small-capacity model architecture and inflexible volume representation.

CT Reconstruction

CAMELTrack: Context-Aware Multi-cue ExpLoitation for Online Multi-Object Tracking

1 code implementation2 May 2025 Vladimir Somers, Baptiste Standaert, Victor Joos, Alexandre Alahi, Christophe De Vleeschouwer

However, the extensive usage of human-crafted rules for temporal associations makes these methods inherently limited in their ability to capture the complex interplay between various tracking cues.

Multi-Object Tracking Online Multi-Object Tracking

Weak-for-Strong: Training Weak Meta-Agent to Harness Strong Executors

1 code implementation7 Apr 2025 Fan Nie, Lan Feng, Haotian Ye, Weixin Liang, Pan Lu, Huaxiu Yao, Alexandre Alahi, James Zou

Efficiently leveraging of the capabilities of contemporary large language models (LLMs) is increasingly challenging, particularly when direct fine-tuning is expensive and often impractical.

FG$^2$: Fine-Grained Cross-View Localization by Fine-Grained Feature Matching

1 code implementation24 Mar 2025 Zimin Xia, Alexandre Alahi

Our method then learns to select features along the height dimension to pool the 3D points to a Bird's-Eye-View (BEV) plane.

Weakly-supervised Learning

Unified Human Localization and Trajectory Prediction with Monocular Vision

1 code implementation5 Mar 2025 Po-Chien Luan, Yang Gao, Celine Demonsant, Alexandre Alahi

On the curated dataset, MT achieves around 12% improvement over baseline models on BEV localization and trajectory prediction.

Prediction Trajectory Prediction

COARSE: Collaborative Pseudo-Labeling with Coarse Real Labels for Off-Road Semantic Segmentation

no code implementations5 Mar 2025 Aurelio Noca, Xianmei Lei, Jonathan Becktor, Jeffrey Edlund, Anna Sabel, Patrick Spieler, Curtis Padgett, Alexandre Alahi, Deegan Atha

Autonomous off-road navigation faces challenges due to diverse, unstructured environments, requiring robust perception with both geometric and semantic understanding.

Domain Adaptation Semantic Segmentation +1

Towards Self-Supervised Covariance Estimation in Deep Heteroscedastic Regression

no code implementations14 Feb 2025 Megh Shukla, Aziz Shameem, Mathieu Salzmann, Alexandre Alahi

We address (2) through a simple neighborhood based heuristic algorithm which results in surprisingly effective pseudo labels for the covariance.

Pseudo Label regression

Multi-Source Urban Traffic Flow Forecasting with Drone and Loop Detector Data

no code implementations7 Jan 2025 Weijiang Xiong, Robert Fonod, Alexandre Alahi, Nikolas Geroliminis

Traffic forecasting is a fundamental task in transportation research, however the scope of current research has mainly focused on a single data modality of loop detectors.

FG^2: Fine-Grained Cross-View Localization by Fine-Grained Feature Matching

no code implementations CVPR 2025 Zimin Xia, Alexandre Alahi

Our method then learns to select features along the height dimension to pool the 3D points to a Bird's-Eye-View (BEV) plane.

Weakly-supervised Learning

TAROT: Targeted Data Selection via Optimal Transport

1 code implementation30 Nov 2024 Lan Feng, Fan Nie, Yuejiang Liu, Alexandre Alahi

Building on this, TAROT uses whitened feature distance to quantify and minimize the optimal transport distance between the selected data and target domains.

motion prediction Semantic Segmentation

Multi-Transmotion: Pre-trained Model for Human Motion Prediction

1 code implementation4 Nov 2024 Yang Gao, Po-Chien Luan, Alexandre Alahi

However, the complexity of human motion have prevented the development of a standardized dataset for human motion prediction, thereby hindering the establishment of pre-trained models.

Human motion prediction motion prediction +2

Strada-LLM: Graph LLM for traffic prediction

no code implementations28 Oct 2024 Seyed Mohamad Moghadas, Yangxintong Lyu, Bruno Cornelis, Alexandre Alahi, Adrian Munteanu

Furthermore, we adopt a lightweight approach for efficient domain adaptation when facing new data distributions in few-shot fashion.

Domain Adaptation Prediction +1

HEADS-UP: Head-Mounted Egocentric Dataset for Trajectory Prediction in Blind Assistance Systems

no code implementations30 Sep 2024 Yasaman Haghighi, Celine Demonsant, Panagiotis Chalimourdas, Maryam Tavasoli Naeini, Jhon Kevin Munoz, Bladimir Bacca, Silvan Suter, Matthieu Gani, Alexandre Alahi

In this paper, we introduce HEADS-UP, the first egocentric dataset collected from head-mounted cameras, designed specifically for trajectory prediction in blind assistance systems.

Prediction Trajectory Prediction

SoccerNet 2024 Challenges Results

1 code implementation16 Sep 2024 Anthony Cioppa, Silvio Giancola, Vladimir Somers, Victor Joos, Floriane Magera, Jan Held, Seyed Abolfazl Ghasemzadeh, Xin Zhou, Karolina Seweryn, Mateusz Kowalczyk, Zuzanna Mróz, Szymon Łukasik, Michał Hałoń, Hassan Mkhallati, Adrien Deliège, Carlos Hinojosa, Karen Sanchez, Amir M. Mansourian, Pierre Miralles, Olivier Barnich, Christophe De Vleeschouwer, Alexandre Alahi, Bernard Ghanem, Marc Van Droogenbroeck, Adam Gorski, Albert Clapés, Andrei Boiarov, Anton Afanasiev, Artur Xarles, Atom Scott, Byoungkwon Lim, Calvin Yeung, Cristian Gonzalez, Dominic Rüfenacht, Enzo Pacilio, Fabian Deuser, Faisal Sami Altawijri, Francisco Cachón, Hankyul Kim, Haobo Wang, Hyeonmin Choe, Hyunwoo J Kim, Il-Min Kim, Jae-Mo Kang, Jamshid Tursunboev, Jian Yang, Jihwan Hong, JiMin Lee, Jing Zhang, Junseok Lee, Kexin Zhang, Konrad Habel, Licheng Jiao, Linyi Li, Marc Gutiérrez-Pérez, Marcelo Ortega, Menglong Li, Milosz Lopatto, Nikita Kasatkin, Nikolay Nemtsev, Norbert Oswald, Oleg Udin, Pavel Kononov, Pei Geng, Saad Ghazai Alotaibi, Sehyung Kim, Sergei Ulasen, Sergio Escalera, Shanshan Zhang, Shuyuan Yang, Sunghwan Moon, Thomas B. Moeslund, Vasyl Shandyba, Vladimir Golovkin, Wei Dai, WonTaek Chung, Xinyu Liu, Yongqiang Zhu, Youngseo Kim, Yuan Li, Yuting Yang, Yuxuan Xiao, Zehua Cheng, Zhihao LI

The SoccerNet 2024 challenges represent the fourth annual video understanding challenges organized by the SoccerNet team.

Action Spotting Dense Video Captioning +2

CODE: Confident Ordinary Differential Editing

1 code implementation22 Aug 2024 Bastien Van Delft, Tommaso Martorella, Alexandre Alahi

However, conditioning on noisy or Out-of-Distribution (OoD) images poses significant challenges, particularly in balancing fidelity to the input and realism of the output.

Conditional Image Generation Image Restoration

MPL: Lifting 3D Human Pose from Multi-view 2D Poses

1 code implementation20 Aug 2024 Seyed Abolfazl Ghasemzadeh, Alexandre Alahi, Christophe De Vleeschouwer

Estimating 3D human poses from 2D images is challenging due to occlusions and projective acquisition.

2D Pose Estimation Pose Estimation

Could ChatGPT get an Engineering Degree? Evaluating Higher Education Vulnerability to AI Assistants

no code implementations7 Aug 2024 Beatriz Borges, Negar Foroutan, Deniz Bayazit, Anna Sotnikova, Syrielle Montariol, Tanya Nazaretzky, Mohammadreza Banaei, Alireza Sakhaeirad, Philippe Servant, Seyed Parsa Neshaei, Jibril Frej, Angelika Romanou, Gail Weiss, Sepideh Mamooler, Zeming Chen, Simin Fan, Silin Gao, Mete Ismayilzada, Debjit Paul, Alexandre Schöpfer, Andrej Janchevski, Anja Tiede, Clarence Linden, Emanuele Troiani, Francesco Salvi, Freya Behrens, Giacomo Orsi, Giovanni Piccioli, Hadrien Sevel, Louis Coulon, Manuela Pineros-Rodriguez, Marin Bonnassies, Pierre Hellich, Puck van Gerwen, Sankalp Gambhir, Solal Pirelli, Thomas Blanchard, Timothée Callens, Toni Abi Aoun, Yannick Calvino Alonso, Yuri Cho, Alberto Chiappa, Antonio Sclocchi, Étienne Bruno, Florian Hofhammer, Gabriel Pescia, Geovani Rizk, Leello Dadi, Lucas Stoffl, Manoel Horta Ribeiro, Matthieu Bovel, Yueyang Pan, Aleksandra Radenovic, Alexandre Alahi, Alexander Mathis, Anne-Florence Bitbol, Boi Faltings, Cécile Hébert, Devis Tuia, François Maréchal, George Candea, Giuseppe Carleo, Jean-Cédric Chappelier, Nicolas Flammarion, Jean-Marie Fürbringer, Jean-Philippe Pellet, Karl Aberer, Lenka Zdeborová, Marcel Salathé, Martin Jaggi, Martin Rajman, Mathias Payer, Matthieu Wyart, Michael Gastpar, Michele Ceriotti, Ola Svensson, Olivier Lévêque, Paolo Ienne, Rachid Guerraoui, Robert West, Sanidhya Kashyap, Valerio Piazza, Viesturs Simanis, Viktor Kuncak, Volkan Cevher, Philippe Schwaller, Sacha Friedli, Patrick Jermann, Tanja Käser, Antoine Bosselut

We investigate the potential scale of this vulnerability by measuring the degree to which AI assistants can complete assessment questions in standard university-level STEM courses.

Forecast-PEFT: Parameter-Efficient Fine-Tuning for Pre-trained Motion Forecasting Models

1 code implementation28 Jul 2024 Jifeng Wang, Kaouther Messaoud, Yuejiang Liu, Juergen Gall, Alexandre Alahi

This tailored strategy, supplemented by our method's capability to efficiently adapt to different datasets, enhances model efficiency and ensures robust performance across datasets without the need for extensive retraining.

Motion Forecasting motion prediction +2

Keypoint Promptable Re-Identification

2 code implementations25 Jul 2024 Vladimir Somers, Christophe De Vleeschouwer, Alexandre Alahi

Inspired by recent work on prompting in vision, we introduce Keypoint Promptable ReID (KPR), a novel formulation of the ReID problem that explicitly complements the input bounding box with a set of semantic keypoints indicating the intended target.

Metric Learning Occluded Person Re-Identification +2

UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction

1 code implementation22 Mar 2024 Lan Feng, Mohammadhossein Bahari, Kaouther Messaoud Ben Amor, Éloi Zablocki, Matthieu Cord, Alexandre Alahi

Vehicle trajectory prediction has increasingly relied on data-driven solutions, but their ability to scale to different data domains and the impact of larger dataset sizes on their generalization remain under-explored.

 Ranked #1 on Trajectory Prediction on nuScenes (using extra training data)

Diversity Prediction +1

Co-Supervised Learning: Improving Weak-to-Strong Generalization with Hierarchical Mixture of Experts

no code implementations23 Feb 2024 Yuejiang Liu, Alexandre Alahi

Steering the behavior of a strong model pre-trained on internet-scale data can be difficult due to the scarcity of competent supervisors.

Mixture-of-Experts

Testing autonomous vehicles and AI: perspectives and challenges from cybersecurity, transparency, robustness and fairness

no code implementations21 Feb 2024 David Fernández Llorca, Ronan Hamon, Henrik Junklewitz, Kathrin Grosse, Lars Kunze, Patrick Seiniger, Robert Swaim, Nick Reed, Alexandre Alahi, Emilia Gómez, Ignacio Sánchez, Akos Kriston

This study explores the complexities of integrating Artificial Intelligence (AI) into Autonomous Vehicles (AVs), examining the challenges introduced by AI components and the impact on testing procedures, focusing on some of the essential requirements for trustworthy AI.

Autonomous Vehicles Decision Making +1

Social-Transmotion: Promptable Human Trajectory Prediction

1 code implementation26 Dec 2023 Saeed Saadatnejad, Yang Gao, Kaouther Messaoud, Alexandre Alahi

We translate the idea of a prompt from Natural Language Processing (NLP) to the task of human trajectory prediction, where a prompt can be a sequence of x-y coordinates on the ground, bounding boxes in the image plane, or body pose keypoints in either 2D or 3D.

Autonomous Vehicles Prediction +1

Images in Discrete Choice Modeling: Addressing Data Isomorphism in Multi-Modality Inputs

1 code implementation22 Dec 2023 Brian Sifringer, Alexandre Alahi

We propose and benchmark two methodologies to address this challenge: architectural design adjustments to segregate redundant information, and isomorphic information mitigation through source information masking and inpainting.

Manipulating Trajectory Prediction with Backdoors

no code implementations21 Dec 2023 Kaouther Messaoud, Kathrin Grosse, Mickael Chen, Matthieu Cord, Patrick Pérez, Alexandre Alahi

In this paper, we focus on backdoors - a security threat acknowledged in other fields but so far overlooked for trajectory prediction.

Autonomous Vehicles Prediction +1

Towards more Practical Threat Models in Artificial Intelligence Security

no code implementations16 Nov 2023 Kathrin Grosse, Lukas Bieringer, Tarek Richard Besold, Alexandre Alahi

Recent works have identified a gap between research and practice in artificial intelligence security: threats studied in academia do not always reflect the practical use and security risks of AI.

JRDB-Traj: A Dataset and Benchmark for Trajectory Forecasting in Crowds

1 code implementation5 Nov 2023 Saeed Saadatnejad, Yang Gao, Hamid Rezatofighi, Alexandre Alahi

To address this, we introduce a novel dataset for end-to-end trajectory forecasting, facilitating the evaluation of models in scenarios involving less-than-ideal preceding modules such as tracking.

Autonomous Navigation Benchmarking +1

TIC-TAC: A Framework for Improved Covariance Estimation in Deep Heteroscedastic Regression

1 code implementation29 Oct 2023 Megh Shukla, Mathieu Salzmann, Alexandre Alahi

However, recent works show that this may result in sub-optimal convergence due to the challenges associated with covariance estimation.

Pose Estimation regression

SoccerNet 2023 Challenges Results

2 code implementations12 Sep 2023 Anthony Cioppa, Silvio Giancola, Vladimir Somers, Floriane Magera, Xin Zhou, Hassan Mkhallati, Adrien Deliège, Jan Held, Carlos Hinojosa, Amir M. Mansourian, Pierre Miralles, Olivier Barnich, Christophe De Vleeschouwer, Alexandre Alahi, Bernard Ghanem, Marc Van Droogenbroeck, Abdullah Kamal, Adrien Maglo, Albert Clapés, Amr Abdelaziz, Artur Xarles, Astrid Orcesi, Atom Scott, Bin Liu, Byoungkwon Lim, Chen Chen, Fabian Deuser, Feng Yan, Fufu Yu, Gal Shitrit, Guanshuo Wang, Gyusik Choi, Hankyul Kim, Hao Guo, Hasby Fahrudin, Hidenari Koguchi, Håkan Ardö, Ibrahim Salah, Ido Yerushalmy, Iftikar Muhammad, Ikuma Uchida, Ishay Be'ery, Jaonary Rabarisoa, Jeongae Lee, Jiajun Fu, Jianqin Yin, Jinghang Xu, Jongho Nang, Julien Denize, Junjie Li, Junpei Zhang, Juntae Kim, Kamil Synowiec, Kenji Kobayashi, Kexin Zhang, Konrad Habel, Kota Nakajima, Licheng Jiao, Lin Ma, Lizhi Wang, Luping Wang, Menglong Li, Mengying Zhou, Mohamed Nasr, Mohamed Abdelwahed, Mykola Liashuha, Nikolay Falaleev, Norbert Oswald, Qiong Jia, Quoc-Cuong Pham, Ran Song, Romain Hérault, Rui Peng, Ruilong Chen, Ruixuan Liu, Ruslan Baikulov, Ryuto Fukushima, Sergio Escalera, Seungcheon Lee, Shimin Chen, Shouhong Ding, Taiga Someya, Thomas B. Moeslund, Tianjiao Li, Wei Shen, Wei zhang, Wei Li, Wei Dai, Weixin Luo, Wending Zhao, Wenjie Zhang, Xinquan Yang, Yanbiao Ma, Yeeun Joo, Yingsen Zeng, Yiyang Gan, Yongqiang Zhu, Yujie Zhong, Zheng Ruan, Zhiheng Li, Zhijian Huang, Ziyu Meng

More information on the tasks, challenges, and leaderboards are available on https://www. soccer-net. org.

Action Spotting Camera Calibration +4

Towards Motion Forecasting with Real-World Perception Inputs: Are End-to-End Approaches Competitive?

1 code implementation15 Jun 2023 Yihong Xu, Loïck Chambon, Éloi Zablocki, Mickaël Chen, Alexandre Alahi, Matthieu Cord, Patrick Pérez

In fact, conventional forecasting methods are usually not trained nor tested in real-world pipelines (e. g., with upstream detection, tracking, and mapping modules).

Benchmarking Motion Forecasting

On Pitfalls of Test-Time Adaptation

1 code implementation6 Jun 2023 Hao Zhao, Yuejiang Liu, Alexandre Alahi, Tao Lin

Test-Time Adaptation (TTA) has recently emerged as a promising approach for tackling the robustness challenge under distribution shifts.

Model Selection Test-time Adaptation

Toward Reliable Human Pose Forecasting with Uncertainty

1 code implementation13 Apr 2023 Saeed Saadatnejad, Mehrshad Mirmohammadi, Matin Daghyani, Parham Saremi, Yashar Zoroofchi Benisi, Amirhossein Alimohammadi, Zahra Tehraninasab, Taylor Mordan, Alexandre Alahi

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.

Human Pose Forecasting

Predicting the long-term collective behaviour of fish pairs with deep learning

no code implementations14 Feb 2023 Vaios Papaspyros, Ramón Escobedo, Alexandre Alahi, Guy Theraulaz, Clément Sire, Francesco Mondada

Although analytical models dominate in studying collective behaviour, this study introduces a deep learning model to assess social interactions in the fish species Hemigrammus rhodostomus.

Deep Learning

1st Workshop on Maritime Computer Vision (MaCVi) 2023: Challenge Results

no code implementations24 Nov 2022 Benjamin Kiefer, Matej Kristan, Janez Perš, Lojze Žust, Fabio Poiesi, Fabio Augusto de Alcantara Andrade, Alexandre Bernardino, Matthew Dawkins, Jenni Raitoharju, Yitong Quan, Adem Atmaca, Timon Höfer, Qiming Zhang, Yufei Xu, Jing Zhang, DaCheng Tao, Lars Sommer, Raphael Spraul, Hangyue Zhao, Hongpu Zhang, Yanyun Zhao, Jan Lukas Augustin, Eui-ik Jeon, Impyeong Lee, Luca Zedda, Andrea Loddo, Cecilia Di Ruberto, Sagar Verma, Siddharth Gupta, Shishir Muralidhara, Niharika Hegde, Daitao Xing, Nikolaos Evangeliou, Anthony Tzes, Vojtěch Bartl, Jakub Špaňhel, Adam Herout, Neelanjan Bhowmik, Toby P. Breckon, Shivanand Kundargi, Tejas Anvekar, Chaitra Desai, Ramesh Ashok Tabib, Uma Mudengudi, Arpita Vats, Yang song, Delong Liu, Yonglin Li, Shuman Li, Chenhao Tan, Long Lan, Vladimir Somers, Christophe De Vleeschouwer, Alexandre Alahi, Hsiang-Wei Huang, Cheng-Yen Yang, Jenq-Neng Hwang, Pyong-Kun Kim, Kwangju Kim, Kyoungoh Lee, Shuai Jiang, Haiwen Li, Zheng Ziqiang, Tuan-Anh Vu, Hai Nguyen-Truong, Sai-Kit Yeung, Zhuang Jia, Sophia Yang, Chih-Chung Hsu, Xiu-Yu Hou, Yu-An Jhang, Simon Yang, Mau-Tsuen Yang

The 1$^{\text{st}}$ Workshop on Maritime Computer Vision (MaCVi) 2023 focused on maritime computer vision for Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicle (USV), and organized several subchallenges in this domain: (i) UAV-based Maritime Object Detection, (ii) UAV-based Maritime Object Tracking, (iii) USV-based Maritime Obstacle Segmentation and (iv) USV-based Maritime Obstacle Detection.

Object object-detection +2

Body Part-Based Representation Learning for Occluded Person Re-Identification

3 code implementations7 Nov 2022 Vladimir Somers, Christophe De Vleeschouwer, Alexandre Alahi

Firstly, individual body part appearance is not as discriminative as global appearance (two distinct IDs might have the same local appearance), this means standard ReID training objectives using identity labels are not adapted to local feature learning.

Human Parsing Occluded Person Re-Identification +3

Motion Style Transfer: Modular Low-Rank Adaptation for Deep Motion Forecasting

1 code implementation6 Nov 2022 Parth Kothari, Danya Li, Yuejiang Liu, Alexandre Alahi

To this end, we introduce two components that exploit our prior knowledge of motion style shifts: (i) a low-rank motion style adapter that projects and adjusts the style features at a low-dimensional bottleneck; and (ii) a modular adapter strategy that disentangles the features of scene context and motion history to facilitate a fine-grained choice of adaptation layers.

Motion Forecasting Motion Style Transfer +2

A generic diffusion-based approach for 3D human pose prediction in the wild

1 code implementation11 Oct 2022 Saeed Saadatnejad, Ali Rasekh, Mohammadreza Mofayezi, Yasamin Medghalchi, Sara Rajabzadeh, Taylor Mordan, Alexandre Alahi

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.

Denoising Human Pose Forecasting +3

SoccerNet 2022 Challenges Results

7 code implementations5 Oct 2022 Silvio Giancola, Anthony Cioppa, Adrien Deliège, Floriane Magera, Vladimir Somers, Le Kang, Xin Zhou, Olivier Barnich, Christophe De Vleeschouwer, Alexandre Alahi, Bernard Ghanem, Marc Van Droogenbroeck, Abdulrahman Darwish, Adrien Maglo, Albert Clapés, Andreas Luyts, Andrei Boiarov, Artur Xarles, Astrid Orcesi, Avijit Shah, Baoyu Fan, Bharath Comandur, Chen Chen, Chen Zhang, Chen Zhao, Chengzhi Lin, Cheuk-Yiu Chan, Chun Chuen Hui, Dengjie Li, Fan Yang, Fan Liang, Fang Da, Feng Yan, Fufu Yu, Guanshuo Wang, H. Anthony Chan, He Zhu, Hongwei Kan, Jiaming Chu, Jianming Hu, Jianyang Gu, Jin Chen, João V. B. Soares, Jonas Theiner, Jorge De Corte, José Henrique Brito, Jun Zhang, Junjie Li, Junwei Liang, Leqi Shen, Lin Ma, Lingchi Chen, Miguel Santos Marques, Mike Azatov, Nikita Kasatkin, Ning Wang, Qiong Jia, Quoc Cuong Pham, Ralph Ewerth, Ran Song, RenGang Li, Rikke Gade, Ruben Debien, Runze Zhang, Sangrok Lee, Sergio Escalera, Shan Jiang, Shigeyuki Odashima, Shimin Chen, Shoichi Masui, Shouhong Ding, Sin-wai Chan, Siyu Chen, Tallal El-Shabrawy, Tao He, Thomas B. Moeslund, Wan-Chi Siu, Wei zhang, Wei Li, Xiangwei Wang, Xiao Tan, Xiaochuan Li, Xiaolin Wei, Xiaoqing Ye, Xing Liu, Xinying Wang, Yandong Guo, YaQian Zhao, Yi Yu, YingYing Li, Yue He, Yujie Zhong, Zhenhua Guo, Zhiheng Li

The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team.

Action Spotting Camera Calibration +3

Safety-compliant Generative Adversarial Networks for Human Trajectory Forecasting

no code implementations25 Sep 2022 Parth Kothari, Alexandre Alahi

Human trajectory forecasting in crowds presents the challenges of modelling social interactions and outputting collision-free multimodal distribution.

Trajectory Forecasting

Pedestrian 3D Bounding Box Prediction

1 code implementation28 Jun 2022 Saeed Saadatnejad, Yi Zhou Ju, Alexandre Alahi

Safety is still the main issue of autonomous driving, and in order to be globally deployed, they need to predict pedestrians' motions sufficiently in advance.

Action Anticipation Autonomous Driving +2

Pedestrian Stop and Go Forecasting with Hybrid Feature Fusion

2 code implementations4 Mar 2022 Dongxu Guo, Taylor Mordan, Alexandre Alahi

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.

Autonomous Driving motion prediction +1

A Shared Representation for Photorealistic Driving Simulators

1 code implementation9 Dec 2021 Saeed Saadatnejad, Siyuan Li, Taylor Mordan, Alexandre Alahi

We build on successful cGAN models to propose a new semantically-aware discriminator that better guides the generator.

Autonomous Vehicles Image Generation +1

Do Pedestrians Pay Attention? Eye Contact Detection in the Wild

1 code implementation8 Dec 2021 Younes Belkada, Lorenzo Bertoni, Romain Caristan, Taylor Mordan, Alexandre Alahi

In urban or crowded environments, humans rely on eye contact for fast and efficient communication with nearby people.

Autonomous Vehicles Contact Detection +2

Vehicle trajectory prediction works, but not everywhere

1 code implementation CVPR 2022 Mohammadhossein Bahari, Saeed Saadatnejad, Ahmad Rahimi, Mohammad Shaverdikondori, Amir-Hossein Shahidzadeh, Seyed-Mohsen Moosavi-Dezfooli, Alexandre Alahi

We further show that the generated scenes (i) are realistic since they do exist in the real world, and (ii) can be used to make existing models more robust, yielding 30-40 reductions in the off-road rate.

Prediction Scene Generation +2

TTT++: When Does Self-Supervised Test-Time Training Fail or Thrive?

1 code implementation NeurIPS 2021 Yuejiang Liu, Parth Kothari, Bastien Van Delft, Baptiste Bellot-Gurlet, Taylor Mordan, Alexandre Alahi

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.

Contrastive Learning Self-Supervised Learning

DriverGym: Democratising Reinforcement Learning for Autonomous Driving

no code implementations12 Nov 2021 Parth Kothari, Christian Perone, Luca Bergamini, Alexandre Alahi, Peter Ondruska

Despite promising progress in reinforcement learning (RL), developing algorithms for autonomous driving (AD) remains challenging: one of the critical issues being the absence of an open-source platform capable of training and effectively validating the RL policies on real-world data.

Autonomous Driving OpenAI Gym +3

SVG-Net: An SVG-based Trajectory Prediction Model

1 code implementation7 Oct 2021 Mohammadhossein Bahari, Vahid Zehtab, Sadegh Khorasani, Sana Ayromlou, Saeed Saadatnejad, Alexandre Alahi

Finally, we illustrate how, by using SVG, one can benefit from datasets and advancements in other research fronts that also utilize the same input format.

Autonomous Driving model +3

Keypoint Communities

1 code implementation ICCV 2021 Duncan Zauss, Sven Kreiss, Alexandre Alahi

We present a fast bottom-up method that jointly detects over 100 keypoints on humans or objects, also referred to as human/object pose estimation.

2D Human Pose Estimation Car Pose Estimation +2

Interpretable Social Anchors for Human Trajectory Forecasting in Crowds

no code implementations CVPR 2021 Parth Kothari, Brian Sifringer, Alexandre Alahi

Human trajectory forecasting in crowds, at its core, is a sequence prediction problem with specific challenges of capturing inter-sequence dependencies (social interactions) and consequently predicting socially-compliant multimodal distributions.

Discrete Choice Models Trajectory Forecasting

Injecting Knowledge in Data-driven Vehicle Trajectory Predictors

1 code implementation8 Mar 2021 Mohammadhossein Bahari, Ismail Nejjar, Alexandre Alahi

On the other hand, recent works use data-driven approaches which can learn complex interactions from the data leading to superior performance.

Model Predictive Control Trajectory Prediction

OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association

6 code implementations3 Mar 2021 Sven Kreiss, Lorenzo Bertoni, Alexandre Alahi

We present a generic neural network architecture that uses Composite Fields to detect and construct a spatio-temporal pose which is a single, connected graph whose nodes are the semantic keypoints (e. g., a person's body joints) in multiple frames.

Car Pose Estimation Keypoint Detection +2

Social NCE: Contrastive Learning of Socially-aware Motion Representations

4 code implementations ICCV 2021 Yuejiang Liu, Qi Yan, Alexandre Alahi

Learning socially-aware motion representations is at the core of recent advances in multi-agent problems, such as human motion forecasting and robot navigation in crowds.

Autonomous Navigation Motion Forecasting +1

Detecting 32 Pedestrian Attributes for Autonomous Vehicles

1 code implementation4 Dec 2020 Taylor Mordan, Matthieu Cord, Patrick Pérez, Alexandre Alahi

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.

Attribute Autonomous Driving +1

Pedestrian Intention Prediction: A Multi-task Perspective

1 code implementation20 Oct 2020 Smail Ait Bouhsain, Saeed Saadatnejad, Alexandre Alahi

This work tries to solve this problem by jointly predicting the intention and visual states of pedestrians.

Autonomous Vehicles Multi-Task Learning +1

Perceiving Traffic from Aerial Images

1 code implementation16 Sep 2020 George Adaimi, Sven Kreiss, Alexandre Alahi

Drones or UAVs, equipped with different sensors, have been deployed in many places especially for urban traffic monitoring or last-mile delivery.

Object object-detection +1

Perceiving Humans: from Monocular 3D Localization to Social Distancing

1 code implementation1 Sep 2020 Lorenzo Bertoni, Sven Kreiss, Alexandre Alahi

Our neural network estimates human 3D body locations and their orientation with a measure of uncertainty.

MonStereo: When Monocular and Stereo Meet at the Tail of 3D Human Localization

2 code implementations25 Aug 2020 Lorenzo Bertoni, Sven Kreiss, Taylor Mordan, Alexandre Alahi

Monocular and stereo visions are cost-effective solutions for 3D human localization in the context of self-driving cars or social robots.

Self-Driving Cars

Human Trajectory Forecasting in Crowds: A Deep Learning Perspective

1 code implementation7 Jul 2020 Parth Kothari, Sven Kreiss, Alexandre Alahi

In this work, we present an in-depth analysis of existing deep learning-based methods for modelling social interactions.

Deep Learning Trajectory Forecasting

Using Image Priors to Improve Scene Understanding

no code implementations2 Oct 2019 Brigit Schroeder, Hanlin Tang, Alexandre Alahi

We propose a simple yet effective method for leveraging these image priors to improve semantic segmentation of images from sequential driving datasets.

Autonomous Driving Decoder +3

Deep Visual Re-Identification with Confidence

1 code implementation11 Jun 2019 George Adaimi, Sven Kreiss, Alexandre Alahi

We argue that such loss function is not suited for the visual re-identification task hence propose to model confidence in the representation learning framework.

Person Re-Identification Representation Learning

Convolutional Relational Machine for Group Activity Recognition

no code implementations CVPR 2019 Sina Mokhtarzadeh Azar, Mina Ghadimi Atigh, Ahmad Nickabadi, Alexandre Alahi

We present an end-to-end deep Convolutional Neural Network called Convolutional Relational Machine (CRM) for recognizing group activities that utilizes the information in spatial relations between individual persons in image or video.

Group Activity Recognition

PifPaf: Composite Fields for Human Pose Estimation

2 code implementations CVPR 2019 Sven Kreiss, Lorenzo Bertoni, Alexandre Alahi

We propose a new bottom-up method for multi-person 2D human pose estimation that is particularly well suited for urban mobility such as self-driving cars and delivery robots.

2D Human Pose Estimation Keypoint Detection +2

Collaborative Sampling in Generative Adversarial Networks

1 code implementation2 Feb 2019 Yuejiang Liu, Parth Kothari, Alexandre Alahi

The standard practice in Generative Adversarial Networks (GANs) discards the discriminator during sampling.

Image Generation

Enhancing Discrete Choice Models with Representation Learning

2 code implementations23 Dec 2018 Brian Sifringer, Virginie Lurkin, Alexandre Alahi

In discrete choice modeling (DCM), model misspecifications may lead to limited predictability and biased parameter estimates.

Discrete Choice Models parameter estimation +1

Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning

7 code implementations24 Sep 2018 Changan Chen, Yuejiang Liu, Sven Kreiss, Alexandre Alahi

We propose to (i) rethink pairwise interactions with a self-attention mechanism, and (ii) jointly model Human-Robot as well as Human-Human interactions in the deep reinforcement learning framework.

Deep Reinforcement Learning Human Dynamics +4

Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks

8 code implementations CVPR 2018 Agrim Gupta, Justin Johnson, Li Fei-Fei, Silvio Savarese, Alexandre Alahi

Understanding human motion behavior is critical for autonomous moving platforms (like self-driving cars and social robots) if they are to navigate human-centric environments.

Collision Avoidance Motion Forecasting +4

CAR-Net: Clairvoyant Attentive Recurrent Network

no code implementations ECCV 2018 Amir Sadeghian, Ferdinand Legros, Maxime Voisin, Ricky Vesel, Alexandre Alahi, Silvio Savarese

We exploit two sources of information: the past motion trajectory of the agent of interest and a wide top-view image of the navigation scene.

Prediction Trajectory Forecasting

Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependencies

no code implementations ICCV 2017 Amir Sadeghian, Alexandre Alahi, Silvio Savarese

To address this challenge, we present a structure of Recurrent Neural Networks (RNN) that jointly reasons on multiple cues over a temporal window.

Unsupervised Learning of Long-Term Motion Dynamics for Videos

no code implementations CVPR 2017 Zelun Luo, Boya Peng, De-An Huang, Alexandre Alahi, Li Fei-Fei

We present an unsupervised representation learning approach that compactly encodes the motion dependencies in videos.

Decoder Representation Learning

Recurrent Attention Models for Depth-Based Person Identification

no code implementations CVPR 2016 Albert Haque, Alexandre Alahi, Li Fei-Fei

We present an attention-based model that reasons on human body shape and motion dynamics to identify individuals in the absence of RGB information, hence in the dark.

Person Identification reinforcement-learning +2

Knowledge Transfer for Scene-specific Motion Prediction

no code implementations22 Mar 2016 Lamberto Ballan, Francesco Castaldo, Alexandre Alahi, Francesco Palmieri, Silvio Savarese

When given a single frame of the video, humans can not only interpret the content of the scene, but also they are able to forecast the near future.

motion prediction Prediction +2

RGB-W: When Vision Meets Wireless

no code implementations ICCV 2015 Alexandre Alahi, Albert Haque, Li Fei-Fei

Inspired by the recent success of RGB-D cameras, we propose the enrichment of RGB data with an additional "quasi-free" modality, namely, the wireless signal (e. g., wifi or Bluetooth) emitted by individuals' cell phones, referred to as RGB-W.

Learning to Track: Online Multi-Object Tracking by Decision Making

no code implementations ICCV 2015 Yu Xiang, Alexandre Alahi, Silvio Savarese

Online Multi-Object Tracking (MOT) has wide applications in time-critical video analysis scenarios, such as robot navigation and autonomous driving.

Autonomous Driving Decision Making +6

Socially-aware Large-scale Crowd Forecasting

no code implementations CVPR 2014 Alexandre Alahi, Vignesh Ramanathan, Li Fei-Fei

In crowded spaces such as city centers or train stations, human mobility looks complex, but is often influenced only by a few causes.

Cannot find the paper you are looking for? You can Submit a new open access paper.