no code implementations • 29 May 2024 • Jiachen Li, Weixi Feng, Tsu-Jui Fu, Xinyi Wang, Sugato Basu, Wenhu Chen, William Yang Wang
In this work, we aim to break the quality bottleneck of a video consistency model (VCM) to achieve $\textbf{both fast and high-quality video generation}$.
1 code implementation • 24 May 2024 • Yu Fu, Wen Xiao, Jia Chen, Jiachen Li, Evangelos Papalexakis, Aichi Chien, Yue Dong
Recent studies reveal that Large Language Models (LLMs) face challenges in balancing safety with utility, particularly when processing long texts for NLP tasks like summarization and translation.
1 code implementation • 9 May 2024 • Jiachen Li, Xinyao Wang, Sijie Zhu, Chia-Wen Kuo, Lu Xu, Fan Chen, Jitesh Jain, Humphrey Shi, Longyin Wen
Recent advancements in Multimodal Large Language Models (LLMs) have focused primarily on scaling by increasing text-image pair data and enhancing LLMs to improve performance on multimodal tasks.
Ranked #1 on Visual Question Answering on MMBench
no code implementations • 26 Mar 2024 • Zhuoyuan Wu, Yuping Wang, Hengbo Ma, Zhaowei Li, Hang Qiu, Jiachen Li
Building on top of cooperative perception, this paper explores the feasibility and effectiveness of cooperative motion prediction.
no code implementations • 16 Mar 2024 • Jiachen Li, Weixi Feng, Wenhu Chen, William Yang Wang
By distilling a latent consistency model (LCM) from a pre-trained teacher latent diffusion model (LDM), LCD facilitates the generation of high-fidelity images within merely 2 to 4 inference steps.
no code implementations • 9 Mar 2024 • Zhuo Xu, Rui Zhou, Yida Yin, Huidong Gao, Masayoshi Tomizuka, Jiachen Li
Data-driven methods have great advantages in modeling complicated human behavioral dynamics and dealing with many human-robot interaction applications.
no code implementations • 28 Feb 2024 • Shiqi Lei, Kanghoon Lee, Linjing Li, Jinkyoo Park, Jiachen Li
Offline learning has become widely used due to its ability to derive effective policies from offline datasets gathered by expert demonstrators without interacting with the environment directly.
no code implementations • 22 Jan 2024 • Jiachen Li, Chuanbo Hua, Hengbo Ma, Jinkyoo Park, Victoria Dax, Mykel J. Kochenderfer
In this paper, we propose a systematic relational reasoning approach with explicit inference of the underlying dynamically evolving relational structures, and we demonstrate its effectiveness for multi-agent trajectory prediction and social robot navigation.
no code implementations • 11 Jan 2024 • Victoria M. Dax, Jiachen Li, Kevin Leahy, Mykel J. Kochenderfer
Graph-structured data is ubiquitous throughout natural and social sciences, and Graph Neural Networks (GNNs) have recently been shown to be effective at solving prediction and inference problems on graph data.
no code implementations • 7 Jan 2024 • Victoria M. Dax, Jiachen Li, Enna Sachdeva, Nakul Agarwal, Mykel J. Kochenderfer
The results show superior performance compared to existing methods in modeling spatio-temporal relations, motion prediction, and identifying time-invariant latent features.
no code implementations • 27 Nov 2023 • Jiachen Li, David Isele, Kanghoon Lee, Jinkyoo Park, Kikuo Fujimura, Mykel J. Kochenderfer
Moreover, we propose an interactivity estimation mechanism based on the difference between predicted trajectories in these two situations, which indicates the degree of influence of the ego agent on other agents.
no code implementations • 16 Nov 2023 • Bingsheng Yao, Guiming Chen, Ruishi Zou, Yuxuan Lu, Jiachen Li, Shao Zhang, Yisi Sang, Sijia Liu, James Hendler, Dakuo Wang
While most existing works on LLM prompting techniques focus only on how to select a better set of data samples inside one single prompt input (In-Context Learning or ICL), why can not we design and leverage multiple prompts together to further improve the LLM's performance?
1 code implementation • 7 Nov 2023 • Jiachen Li, Roberto Henschel, Vidit Goel, Marianna Ohanyan, Shant Navasardyan, Humphrey Shi
To remedy this deficiency, we propose Video Instance Matting~(VIM), that is, estimating alpha mattes of each instance at each frame of a video sequence.
1 code implementation • 26 Oct 2023 • Jiachen Li, Xiaojin Gong
Although prompt learning has enabled a recent work named CLIP-ReID to achieve promising performance, the underlying mechanisms and the necessity of prompt learning remain unclear due to the absence of semantic labels in ReID tasks.
Ranked #1 on Unsupervised Vehicle Re-Identification on VeRi-776
Contrastive Learning Unsupervised Person Re-Identification +1
no code implementations • 14 Oct 2023 • Jiachen Li, Qiaozi Gao, Michael Johnston, Xiaofeng Gao, Xuehai He, Suhaila Shakiah, Hangjie Shi, Reza Ghanadan, William Yang Wang
In this work, we tackle the problem of training a robot to understand multimodal prompts, interleaving vision signals with text descriptions.
1 code implementation • 25 Sep 2023 • Bernard Lange, Jiachen Li, Mykel J. Kochenderfer
We introduce the Scene Informer, a unified approach for predicting both observed agent trajectories and inferring occlusions in a partially observable setting.
no code implementations • 14 Sep 2023 • Yang Li, Fan Zhong, Xin Wang, Shuangbing Song, Jiachen Li, Xueying Qin, Changhe Tu
The limitations of previous scoring methods and error metrics are analyzed, based on which we introduce our improved evaluation methods.
1 code implementation • 12 Sep 2023 • Enna Sachdeva, Nakul Agarwal, Suhas Chundi, Sean Roelofs, Jiachen Li, Mykel Kochenderfer, Chiho Choi, Behzad Dariush
The widespread adoption of commercial autonomous vehicles (AVs) and advanced driver assistance systems (ADAS) may largely depend on their acceptance by society, for which their perceived trustworthiness and interpretability to riders are crucial.
no code implementations • 19 Jul 2023 • Kanghoon Lee, Jiachen Li, David Isele, Jinkyoo Park, Kikuo Fujimura, Mykel J. Kochenderfer
Although deep reinforcement learning (DRL) has shown promising results for autonomous navigation in interactive traffic scenarios, existing work typically adopts a fixed behavior policy to control social vehicles in the training environment.
1 code implementation • 8 Jun 2023 • Jiachen Li, Jitesh Jain, Humphrey Shi
In this paper, we propose the Matting Anything Model (MAM), an efficient and versatile framework for estimating the alpha matte of any instance in an image with flexible and interactive visual or linguistic user prompt guidance.
no code implementations • 1 Jun 2023 • Jiachen Li, Xinwei Shi, Feiyu Chen, Jonathan Stroud, Zhishuai Zhang, Tian Lan, Junhua Mao, Jeonhyung Kang, Khaled S. Refaat, Weilong Yang, Eugene Ie, CongCong Li
Accurate understanding and prediction of human behaviors are critical prerequisites for autonomous vehicles, especially in highly dynamic and interactive scenarios such as intersections in dense urban areas.
1 code implementation • 11 Mar 2023 • Simon Graham, Quoc Dang Vu, Mostafa Jahanifar, Martin Weigert, Uwe Schmidt, Wenhua Zhang, Jun Zhang, Sen yang, Jinxi Xiang, Xiyue Wang, Josef Lorenz Rumberger, Elias Baumann, Peter Hirsch, Lihao Liu, Chenyang Hong, Angelica I. Aviles-Rivero, Ayushi Jain, Heeyoung Ahn, Yiyu Hong, Hussam Azzuni, Min Xu, Mohammad Yaqub, Marie-Claire Blache, Benoît Piégu, Bertrand Vernay, Tim Scherr, Moritz Böhland, Katharina Löffler, Jiachen Li, Weiqin Ying, Chixin Wang, Dagmar Kainmueller, Carola-Bibiane Schönlieb, Shuolin Liu, Dhairya Talsania, Yughender Meda, Prakash Mishra, Muhammad Ridzuan, Oliver Neumann, Marcel P. Schilling, Markus Reischl, Ralf Mikut, Banban Huang, Hsiang-Chin Chien, Ching-Ping Wang, Chia-Yen Lee, Hong-Kun Lin, Zaiyi Liu, Xipeng Pan, Chu Han, Jijun Cheng, Muhammad Dawood, Srijay Deshpande, Raja Muhammad Saad Bashir, Adam Shephard, Pedro Costa, João D. Nunes, Aurélio Campilho, Jaime S. Cardoso, Hrishikesh P S, Densen Puthussery, Devika R G, Jiji C V, Ye Zhang, Zijie Fang, Zhifan Lin, Yongbing Zhang, Chunhui Lin, Liukun Zhang, Lijian Mao, Min Wu, Vi Thi-Tuong Vo, Soo-Hyung Kim, Taebum Lee, Satoshi Kondo, Satoshi Kasai, Pranay Dumbhare, Vedant Phuse, Yash Dubey, Ankush Jamthikar, Trinh Thi Le Vuong, Jin Tae Kwak, Dorsa Ziaei, Hyun Jung, Tianyi Miao, David Snead, Shan E Ahmed Raza, Fayyaz Minhas, Nasir M. Rajpoot
Nuclear detection, segmentation and morphometric profiling are essential in helping us further understand the relationship between histology and patient outcome.
no code implementations • 29 Nov 2022 • Jiachen Li, Edwin Zhang, Ming Yin, Qinxun Bai, Yu-Xiang Wang, William Yang Wang
Behavior constrained policy optimization has been demonstrated to be a successful paradigm for tackling Offline Reinforcement Learning.
1 code implementation • 22 Nov 2022 • Jiachen Li, Menglin Wang, Xiaojin Gong
To this end, we build a dual-branch network architecture based upon a modified Vision Transformer (ViT).
2 code implementations • CVPR 2023 • Jitesh Jain, Jiachen Li, MangTik Chiu, Ali Hassani, Nikita Orlov, Humphrey Shi
However, such panoptic architectures do not truly unify image segmentation because they need to be trained individually on the semantic, instance, or panoptic segmentation to achieve the best performance.
Ranked #1 on Panoptic Segmentation on COCO minival
no code implementations • 13 Oct 2022 • Jiaqi Han, Wenbing Huang, Hengbo Ma, Jiachen Li, Joshua B. Tenenbaum, Chuang Gan
Graph Neural Networks (GNNs) have become a prevailing tool for learning physical dynamics.
no code implementations • 27 Sep 2022 • Maneekwan Toyungyernsub, Esen Yel, Jiachen Li, Mykel J. Kochenderfer
Detection and segmentation of moving obstacles, along with prediction of the future occupancy states of the local environment, are essential for autonomous vehicles to proactively make safe and informed decisions.
no code implementations • 22 Sep 2022 • Srikanth Malla, Chiho Choi, Isht Dwivedi, Joon Hee Choi, Jiachen Li
We make this data available to the community for further research.
1 code implementation • 26 Aug 2022 • Jiachen Li, Vidit Goel, Marianna Ohanyan, Shant Navasardyan, Yunchao Wei, Humphrey Shi
In this paper, we propose VMFormer: a transformer-based end-to-end method for video matting.
no code implementations • 23 Aug 2022 • Fan-Yun Sun, Isaac Kauvar, Ruohan Zhang, Jiachen Li, Mykel Kochenderfer, Jiajun Wu, Nick Haber
Modeling multi-agent systems requires understanding how agents interact.
no code implementations • 10 Aug 2022 • Jiachen Li, Chuanbo Hua, Jinkyoo Park, Hengbo Ma, Victoria Dax, Mykel J. Kochenderfer
While the modeling of pair-wise relations has been widely studied in multi-agent interacting systems, its ability to capture higher-level and larger-scale group-wise activities is limited.
3 code implementations • 14 Jul 2022 • Pengfei Chen, Xuehui Yu, Xumeng Han, Najmul Hassan, Kai Wang, Jiachen Li, Jian Zhao, Humphrey Shi, Zhenjun Han, Qixiang Ye
However, the performance gap between point supervised object detection (PSOD) and bounding box supervised detection remains large.
1 code implementation • 10 Jun 2022 • Xinyi Wang, Michael Saxon, Jiachen Li, Hongyang Zhang, Kun Zhang, William Yang Wang
While machine learning models rapidly advance the state-of-the-art on various real-world tasks, out-of-domain (OOD) generalization remains a challenging problem given the vulnerability of these models to spurious correlations.
no code implementations • 24 May 2022 • Jiachen Li, Ye Yuan, Hong-Bin Shen
Symbolic Regression (SR) is a type of regression analysis to automatically find the mathematical expression that best fits the data.
5 code implementations • CVPR 2023 • Ali Hassani, Steven Walton, Jiachen Li, Shen Li, Humphrey Shi
We present Neighborhood Attention (NA), the first efficient and scalable sliding-window attention mechanism for vision.
Ranked #119 on Semantic Segmentation on ADE20K
no code implementations • CVPR 2022 • Jiachen Li, Bin Wang, Shiqiang Zhu, Xin Cao, Fan Zhong, Wenxuan Chen, Te Li, Jason Gu, Xueying Qin
Our new benchmark dataset contains 20 textureless objects, 22 scenes, 404 video sequences and 126K images captured in real scenes.
no code implementations • 5 Mar 2022 • Jiachen Li, Haiming Gang, Hengbo Ma, Masayoshi Tomizuka, Chiho Choi
We propose a novel approach for important object identification in egocentric driving scenarios with relational reasoning on the objects in the scene.
1 code implementation • 28 Feb 2022 • Jiachen Li, Chixin Wang, Banban Huang, Zekun Zhou
This manuscript gives a brief description of the algorithm used to participate in CoNIC Challenge 2022.
1 code implementation • 15 Jan 2022 • Menglin Wang, Jiachen Li, Baisheng Lai, Xiaojin Gong, Xian-Sheng Hua
Assisted with the camera-aware proxies, we design two proxy-level contrastive learning losses that are, respectively, based on offline and online association results.
no code implementations • CVPR 2022 • Hengbo Ma, Jiachen Li, Ramtin Hosseini, Masayoshi Tomizuka, Chiho Choi
Obtaining accurate and diverse human motion prediction is essential to many industrial applications, especially robotics and autonomous driving.
1 code implementation • CVPR 2022 • Jiaxian Guo, Jiachen Li, Huan Fu, Mingming Gong, Kun Zhang, DaCheng Tao
Unsupervised image-to-image (I2I) translation aims to learn a domain mapping function that can preserve the semantics of the input images without paired data.
1 code implementation • arXiv 2021 • Jitesh Jain, Anukriti Singh, Nikita Orlov, Zilong Huang, Jiachen Li, Steven Walton, Humphrey Shi
To achieve this, we propose SeMask, a simple and effective framework that incorporates semantic information into the encoder with the help of a semantic attention operation.
Ranked #10 on Semantic Segmentation on Cityscapes val
no code implementations • 22 Oct 2021 • Jiachen Li, Shuo Cheng, Zhenyu Liao, Huayan Wang, William Yang Wang, Qinxun Bai
Improving the sample efficiency of reinforcement learning algorithms requires effective exploration.
no code implementations • 18 Oct 2021 • Akshay Dharmavaram, Tejus Gupta, Jiachen Li, Katia P. Sycara
We show that our method (SS-MAIL) outperforms prior state-of-the-art methods on real-world prediction tasks, as well as on custom-designed synthetic experiments.
no code implementations • 29 Sep 2021 • Rui Zhou, HongYu Zhou, Huidong Gao, Masayoshi Tomizuka, Jiachen Li, Zhuo Xu
Accurate, long-term forecasting of pedestrian trajectories in highly dynamic and interactive scenes is a long-standing challenge.
4 code implementations • 9 Sep 2021 • Jiachen Li, Ali Hassani, Steven Walton, Humphrey Shi
MLP-based architectures, which consist of a sequence of consecutive multi-layer perceptron blocks, have recently been found to reach comparable results to convolutional and transformer-based methods.
Ranked #8 on Image Classification on Flowers-102 (using extra training data)
no code implementations • ICCV 2021 • Harshayu Girase, Haiming Gang, Srikanth Malla, Jiachen Li, Akira Kanehara, Karttikeya Mangalam, Chiho Choi
We also propose a model that jointly performs trajectory and intention prediction, showing that recurrently reasoning about intention can assist with trajectory prediction.
no code implementations • ICCV 2021 • Jiachen Li, Fan Yang, Hengbo Ma, Srikanth Malla, Masayoshi Tomizuka, Chiho Choi
Motion forecasting plays a significant role in various domains (e. g., autonomous driving, human-robot interaction), which aims to predict future motion sequences given a set of historical observations.
no code implementations • 2 Aug 2021 • Cheng Gong, Zirui Li, Xingyu Zhou, Jiachen Li, Jianwei Gong, Junhui Zhou
Omni-directional mobile robot (OMR) systems have been very popular in academia and industry for their superb maneuverability and flexibility.
no code implementations • 24 Jun 2021 • Lianzhen Wei, Zirui Li, Jianwei Gong, Cheng Gong, Jiachen Li
Due to the complex and dynamic character of intersection scenarios, the autonomous driving strategy at intersections has been a difficult problem and a hot point in the research of intelligent transportation systems in recent years.
1 code implementation • 19 Jun 2021 • Vidit Goel, Jiachen Li, Shubhika Garg, Harsh Maheshwari, Humphrey Shi
Our method improves the masks from segmentation and propagation branches in an online manner using the Mask Selection Network (MSN) hence limiting the noise accumulation during mask tracking.
Ranked #26 on Video Instance Segmentation on YouTube-VIS validation
no code implementations • 5 Jun 2021 • Defu Cao, Jiachen Li, Hengbo Ma, Masayoshi Tomizuka
To this end, we propose a Spectral Temporal Graph Neural Network (SpecTGNN), which can capture inter-agent correlations and temporal dependency simultaneously in frequency domain in addition to time domain.
no code implementations • 26 May 2021 • Jiachen Li, Yuan Lin, Rongrong Liu, Chiu Man Ho, Humphrey Shi
Segmentation-based scene text detection methods have been widely adopted for arbitrary-shaped text detection recently, since they make accurate pixel-level predictions on curved text instances and can facilitate real-time inference without time-consuming processing on anchors.
1 code implementation • 29 Apr 2021 • Jiachen Li, Bowen Cheng, Rogerio Feris, JinJun Xiong, Thomas S. Huang, Wen-mei Hwu, Humphrey Shi
Current anchor-free object detectors are quite simple and effective yet lack accurate label assignment methods, which limits their potential in competing with classic anchor-based models that are supported by well-designed assignment methods based on the Intersection-over-Union~(IoU) metric.
8 code implementations • 12 Apr 2021 • Ali Hassani, Steven Walton, Nikhil Shah, Abulikemu Abuduweili, Jiachen Li, Humphrey Shi
Our models are flexible in terms of model size, and can have as little as 0. 28M parameters while achieving competitive results.
Ranked #1 on Image Classification on Flowers-102 (using extra training data)
Fine-Grained Image Classification Superpixel Image Classification
no code implementations • 18 Feb 2021 • Jiachen Li, Hengbo Ma, Zhihao Zhang, Jinning Li, Masayoshi Tomizuka
Due to the existence of frequent interactions and uncertainty in the scene evolution, it is desired for the prediction system to enable relational reasoning on different entities and provide a distribution of future trajectories for each agent.
no code implementations • 1 Jan 2021 • Jiaxian Guo, Jiachen Li, Mingming Gong, Huan Fu, Kun Zhang, DaCheng Tao
Unsupervised image-to-image (I2I) translation, which aims to learn a domain mapping function without paired data, is very challenging because the function is highly under-constrained.
no code implementations • CVPR 2021 • Chiho Choi, Joon Hee Choi, Jiachen Li, Srikanth Malla
At test time, a single input modality (e. g., LiDAR data) is required to generate predictions from the input perspective (i. e., in the LiDAR space), while taking advantages from the model trained with multiple sensor modalities.
no code implementations • 9 Nov 2020 • Xiaobai Ma, Jiachen Li, Mykel J. Kochenderfer, David Isele, Kikuo Fujimura
Deep reinforcement learning (DRL) provides a promising way for learning navigation in complex autonomous driving scenarios.
no code implementations • 1 Apr 2020 • Chiho Choi, Joon Hee Choi, Srikanth Malla, Jiachen Li
At test time, a single input modality (e. g., LiDAR data) is required to generate predictions from the input perspective (i. e., in the LiDAR space), while taking advantages from the model trained with multiple sensor modalities.
no code implementations • NeurIPS 2020 • Jiachen Li, Fan Yang, Masayoshi Tomizuka, Chiho Choi
In this paper, we propose a generic trajectory forecasting framework (named EvolveGraph) with explicit relational structure recognition and prediction via latent interaction graphs among multiple heterogeneous, interactive agents.
Ranked #12 on Trajectory Prediction on Stanford Drone
no code implementations • 14 Feb 2020 • Jiachen Li, Hengbo Ma, Zhihao Zhang, Masayoshi Tomizuka
Effective understanding of the environment and accurate trajectory prediction of surrounding dynamic obstacles are indispensable for intelligent mobile systems (like autonomous vehicles and social robots) to achieve safe and high-quality planning when they navigate in highly interactive and crowded scenarios.
no code implementations • NeurIPS 2020 • Jiachen Li, Quan Vuong, Shuang Liu, Minghua Liu, Kamil Ciosek, Keith Ross, Henrik Iskov Christensen, Hao Su
To perform well, the policy must infer the task identity from collected transitions by modelling its dependency on states, actions and rewards.
2 code implementations • 20 Sep 2019 • Xiaofan Zhang, Haoming Lu, Cong Hao, Jiachen Li, Bowen Cheng, Yuhong Li, Kyle Rupnow, JinJun Xiong, Thomas Huang, Honghui Shi, Wen-mei Hwu, Deming Chen
Object detection and tracking are challenging tasks for resource-constrained embedded systems.
no code implementations • 23 Aug 2019 • Jiachen Li, Wei Zhan, Yeping Hu, Masayoshi Tomizuka
The framework can incorporate an arbitrary prediction model as the implicit proposal distribution of the CMSMC method.
1 code implementation • 25 Jun 2019 • Xiaofan Zhang, Cong Hao, Haoming Lu, Jiachen Li, Yuhong Li, Yuchen Fan, Kyle Rupnow, JinJun Xiong, Thomas Huang, Honghui Shi, Wen-mei Hwu, Deming Chen
Developing artificial intelligence (AI) at the edge is always challenging, since edge devices have limited computation capability and memory resources but need to meet demanding requirements, such as real-time processing, high throughput performance, and high inference accuracy.
no code implementations • 5 May 2019 • Jiachen Li, Hengbo Ma, Masayoshi Tomizuka
Effective understanding of the environment and accurate trajectory prediction of surrounding dynamic obstacles are critical for intelligent systems such as autonomous vehicles and wheeled mobile robotics navigating in complex scenarios to achieve safe and high-quality decision making, motion planning and control.
Ranked #14 on Trajectory Prediction on Stanford Drone
no code implementations • 2 May 2019 • Jiachen Li, Hengbo Ma, Wei Zhan, Masayoshi Tomizuka
In order to tackle the task of probabilistic prediction for multiple, interactive entities, we propose a coordination and trajectory prediction system (CTPS), which has a hierarchical structure including a macro-level coordination recognition module and a micro-level subtle pattern prediction module which solves a probabilistic generation task.
no code implementations • CVPR 2019 • Xingran Zhou, Siyu Huang, Bin Li, Yingming Li, Jiachen Li, Zhongfei Zhang
This paper presents a novel method to manipulate the visual appearance (pose and attribute) of a person image according to natural language descriptions.
no code implementations • 4 Apr 2019 • Jiachen Li, Hengbo Ma, Masayoshi Tomizuka
In order to enable high-quality decision making and motion planning of intelligent systems such as robotics and autonomous vehicles, accurate probabilistic predictions for surrounding interactive objects is a crucial prerequisite.
no code implementations • 6 Nov 2018 • Rui Qian, Yunchao Wei, Honghui Shi, Jiachen Li, Jiaying Liu, Thomas Huang
Semantic scene parsing is suffering from the fact that pixel-level annotations are hard to be collected.
no code implementations • 10 Sep 2018 • Wei Zhan, Liting Sun, Yeping Hu, Jiachen Li, Masayoshi Tomizuka
Modified methods based on PGM, NN and IRL are provided to generate probabilistic reaction predictions in an exemplar scenario of nudging from a highway ramp.
no code implementations • 9 Sep 2018 • Jiachen Li, Hengbo Ma, Wei Zhan, Masayoshi Tomizuka
Accurate and robust recognition and prediction of traffic situation plays an important role in autonomous driving, which is a prerequisite for risk assessment and effective decision making.