Search Results for author:
Found 20 papers, 13 papers with code
AMM: Adaptive Modularized Reinforcement Model for Multi-city Traffic Signal Control
One possible solution is TSC domain adaptation, which adapts trained models to target environments and reduces the number of interactions and the training cost.
CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding
However, because of the inherent limitation of MCQ-based evaluation and the increasing reasoning ability of MLLMs, models can give the current answer purely by combining short video understanding with elimination, without genuinely understanding the video content.
CorrAdaptor: Adaptive Local Context Learning for Correspondence Pruning
In the fields of computer vision and robotics, accurate pixel-level correspondences are essential for enabling advanced tasks such as structure-from-motion and simultaneous localization and mapping.
UniTE: A Survey and Unified Pipeline for Pre-training Spatiotemporal Trajectory Embeddings
Further, we present a unified and modular pipeline with publicly available underlying code, simplifying the process of constructing and evaluating methods for pre-training trajectory embeddings.
EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptation
In this report, we present our solutions to the EgoVis Challenges in CVPR 2024, including five tracks in the Ego4D challenge and three tracks in the EPIC-Kitchens challenge.
Ranked #1 on
Long Term Action Anticipation
on Ego4D
(using extra training data)
https://paperswithcode.com/paper/negatives-make-a-positive-an-embarrassingly
Existing IMVC methods primarily suffer from two issues: 1) Imputation-based methods inevitably introduce inaccurate imputations, which in turn degrade clustering performance; 2) Imputation-free methods are susceptible to unbalanced information among views and fail to fully exploit shared information.
Deep Variational Incomplete Multi-View Clustering: Exploring Shared Clustering Structures
Existing IMVC methods primarily suffer from two issues: 1) Imputation-based methods inevitably introduce inaccurate imputations, which in turn degrade clustering performance; 2) Imputation-free methods are susceptible to unbalanced information among views and fail to fully exploit shared information.
PreSight: Enhancing Autonomous Vehicle Perception with City-Scale NeRF Priors
Autonomous vehicles rely extensively on perception systems to navigate and interpret their surroundings.
DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models
A primary hurdle of autonomous driving in urban environments is understanding complex and long-tail scenarios, such as challenging road conditions and delicate human behaviors.
StreamMapNet: Streaming Mapping Network for Vectorized Online HD Map Construction
This approach limits their stability and performance in complex scenarios such as occlusions, largely due to the absence of temporal information.
Neural Map Prior for Autonomous Driving
To the best of our knowledge, this is the first learning-based system for creating a global map prior.
Deep Double Incomplete Multi-view Multi-label Learning with Incomplete Labels and Missing Views
View missing and label missing are two challenging problems in the applications of multi-view multi-label classification scenery.
CBLab: Supporting the Training of Large-scale Traffic Control Policies with Scalable Traffic Simulation
To the best of our knowledge, CBLab is the first infrastructure supporting traffic control policy optimization in large-scale urban scenarios.
VectorMapNet: End-to-end Vectorized HD Map Learning
To the best of our knowledge, VectorMapNet is the first work designed towards end-to-end vectorized map learning from onboard observations.
Ranked #1 on
HD semantic map learning
on nuScenes
Multimodal Motion Prediction with Stacked Transformers
Predicting multiple plausible future trajectories of the nearby vehicles is crucial for the safety of autonomous driving.
Increasing Data Efficiency of Driving Agent By World Model
To this end we proposed a world model to model popular reinforcement learning environments through compressed spatio-temporal representations, which allow model-free method learning behaviors from imagined outcomes to increase sample-efficiency.
Bidirectional Convolutional Poisson Gamma Dynamical Systems
Incorporating the natural document-sentence-word structure into hierarchical Bayesian modeling, we propose convolutional Poisson gamma dynamical systems (PGDS) that introduce not only word-level probabilistic convolutions, but also sentence-level stochastic temporal transitions.
signADAM: Learning Confidences for Deep Neural Networks
In this paper, we propose a new first-order gradient-based algorithm to train deep neural networks.
