Search Results for author:
Found 54 papers, 30 papers with code
4D-CS: Exploiting Cluster Prior for 4D Spatio-Temporal LiDAR Semantic Segmentation
Semantic segmentation of LiDAR points has significant value for autonomous driving and mobile robot systems.
Efficient Scaling of Diffusion Transformers for Text-to-Image Generation
We empirically study the scaling properties of various Diffusion Transformers (DiTs) for text-to-image generation by performing extensive and rigorous ablations, including training scaled DiTs ranging from 0. 3B upto 8B parameters on datasets up to 600M images.
LOMA: Language-assisted Semantic Occupancy Network via Triplane Mamba
Nowadays, conventional methods usually project the image-based vision features to 3D space and learn the geometric information through the attention mechanism, enabling the 3D semantic occupancy prediction.
A Survey on Large Language Model-empowered Autonomous Driving
We further analyze the potential limitations and challenges that LLMs may encounter in promoting the development of AD technology.
Integrating Controllable Motion Skills from Demonstrations
The expanding applications of legged robots require their mastery of versatile motion skills.
StreamMOS: Streaming Moving Object Segmentation with Multi-View Perception and Dual-Span Memory
Specifically, we utilize a short-term memory to convey historical features, which can be regarded as spatial prior of moving objects and adopted to enhance current inference by temporal fusion.
KiGRAS: Kinematic-Driven Generative Model for Realistic Agent Simulation
By establishing physical causality from actions (cause) to trajectories (effect) through the kinematic model, KiGRAS eliminates massive redundant trajectories.
FlowTrack: Point-level Flow Network for 3D Single Object Tracking
Specifically, by estimating the flow for each point in the target, our method could capture the local motion details of target, thereby improving the tracking performance.
StreamMOTP: Streaming and Unified Framework for Joint 3D Multi-Object Tracking and Trajectory Prediction
3D multi-object tracking and trajectory prediction are two crucial modules in autonomous driving systems.
Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset
More specifically, MARS is collected with a fleet of autonomous vehicles driving within a certain geographical area.
DEER: A Delay-Resilient Framework for Reinforcement Learning with Variable Delays
Classic reinforcement learning (RL) frequently confronts challenges in tasks involving delays, which cause a mismatch between received observations and subsequent actions, thereby deviating from the Markov assumption.
Dense Connector for MLLMs
We witness the rise of larger and higher-quality instruction datasets, as well as the involvement of larger-sized LLMs.
ART3D: 3D Gaussian Splatting for Text-Guided Artistic Scenes Generation
In this paper, we explore the existing challenges in 3D artistic scene generation by introducing ART3D, a novel framework that combines diffusion models and 3D Gaussian splatting techniques.
Mask-ControlNet: Higher-Quality Image Generation with An Additional Mask Prompt
Then, the object images are employed as additional prompts to facilitate the diffusion model to better understand the relationship between foreground and background regions during image generation.
FairRAG: Fair Human Generation via Fair Retrieval Augmentation
In this work, we introduce Fair Retrieval Augmented Generation (FairRAG), a novel framework that conditions pre-trained generative models on reference images retrieved from an external image database to improve fairness in human generation.
Sketch-to-Architecture: Generative AI-aided Architectural Design
Recently, the development of large-scale models has paved the way for various interdisciplinary research, including architecture.
Discover and Mitigate Multiple Biased Subgroups in Image Classifiers
Discovering biased subgroups is the key to understanding models' failure modes and further improving models' robustness.
Learning Dual-Level Deformable Implicit Representation for Real-World Scale Arbitrary Super-Resolution
The appearance embedding models the characteristics of low-resolution inputs to deal with photometric variations at different scales, and the pixel-based deformation field learns RGB differences which result from the deviations between the real-world and simulated degradations at arbitrary coordinates.
SeqTrack3D: Exploring Sequence Information for Robust 3D Point Cloud Tracking
Most existing methods perform tracking between two consecutive frames while ignoring the motion patterns of the target over a series of frames, which would cause performance degradation in the scenes with sparse points.
Pareto-based Multi-Objective Recommender System with Forgetting Curve
Considering recency effect in memories, we propose a forgetting model based on Ebbinghaus Forgetting Curve to cope with negative feedback.
Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer Learning
In this paper, we present a novel Spatial-Temporal Side Network for memory-efficient fine-tuning large image models to video understanding, named Side4Video.
Ranked #3 on
Action Recognition
on Something-Something V1
Mixed Attention Network for Cross-domain Sequential Recommendation
Recent proposed cross-domain sequential recommendation models such as PiNet and DASL have a common drawback relying heavily on overlapped users in different domains, which limits their usage in practical recommender systems.
Inverse Learning with Extremely Sparse Feedback for Recommendation
In this paper, we propose a meta-learning method to annotate the unlabeled data from loss and gradient perspectives, which considers the noises in both positive and negative instances.
Distance-rank Aware Sequential Reward Learning for Inverse Reinforcement Learning with Sub-optimal Demonstrations
Considering that obtaining expert demonstrations can be costly, the focus of current IRL techniques is on learning a better-than-demonstrator policy using a reward function derived from sub-optimal demonstrations.
Skip-Plan: Procedure Planning in Instructional Videos via Condensed Action Space Learning
By this means, our model explores all sorts of reliable sub-relations within an action sequence in the condensed action space.
SoccerNet 2023 Challenges Results
More information on the tasks, challenges, and leaderboards are available on https://www. soccer-net. org.
Motion-to-Matching: A Mixed Paradigm for 3D Single Object Tracking
3D single object tracking with LiDAR points is an important task in the computer vision field.
STTracker: Spatio-Temporal Tracker for 3D Single Object Tracking
Previous methods usually input the last two frames and use the predicted box to get the template point cloud in previous frame and the search area point cloud in the current frame respectively, then use similarity-based or motion-based methods to predict the current box.
SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving
Monocular scene understanding is a foundational component of autonomous systems.
3D Semantic Scene Completion
3D Semantic Scene Completion from a single 2D image
Normalization Enhances Generalization in Visual Reinforcement Learning
Though normalization techniques have demonstrated huge success in supervised and unsupervised learning, their applications in visual RL are still scarce.
LayerDiffusion: Layered Controlled Image Editing with Diffusion Models
During the diffusion process, an iterative guidance strategy is used to generate a final image that aligns with the textual description.
MMF-Track: Multi-modal Multi-level Fusion for 3D Single Object Tracking
To overcome the limitations of geometry matching, we propose a Multi-modal Multi-level Fusion Tracker (MMF-Track), which exploits the image texture and geometry characteristic of point clouds to track 3D target.
Dual-interest Factorization-heads Attention for Sequential Recommendation
In this paper, we propose Dual-interest Factorization-heads Attention for Sequential Recommendation (short for DFAR) consisting of feedback-aware encoding layer, dual-interest disentangling layer and prediction layer.
You Only Need a Good Embeddings Extractor to Fix Spurious Correlations
With experiments on a wide range of pre-trained models and pre-training datasets, we show that the capacity of the pre-training model and the size of the pre-training dataset matters.
A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others
Key to advancing the reliability of vision systems is understanding whether existing methods can overcome multiple shortcuts or struggle in a Whac-A-Mole game, i. e., where mitigating one shortcut amplifies reliance on others.
Ranked #1 on
Out-of-Distribution Generalization
on ImageNet-W
Multiple Object Tracking Challenge Technical Report for Team MT_IoT
This is a brief technical report of our proposed method for Multiple-Object Tracking (MOT) Challenge in Complex Environments.
Ranked #8 on
Multi-Object Tracking
on DanceTrack
(using extra training data)
SoccerNet 2022 Challenges Results
The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team.
Exploiting More Information in Sparse Point Cloud for 3D Single Object Tracking
Meanwhile, the encoder applies the attention on multi-scale features to compensate for the lack of information caused by the sparsity of point cloud and the single scale of features.
Rethinking Dimensionality Reduction in Grid-based 3D Object Detection
In MDRNet, the Spatial-aware Dimensionality Reduction (SDR) is designed to dynamically focus on the valuable parts of the object during voxel-to-BEV feature transformation.
Mutual Harmony: Sequential Recommendation with Dual Contrastive Network
Such user-centric recommendation will make it impossible for the provider to expose their new items, failing to consider the accordant interactions between user and item dimensions.
Discover and Mitigate Unknown Biases with Debiasing Alternate Networks
By training in an alternate manner, the discoverer tries to find multiple unknown biases of the classifier without any annotations of biases, and the classifier aims at unlearning the biases identified by the discoverer.
Ranked #1 on
Out-of-Distribution Generalization
on ImageNet-W
Enhancing Multi-view Stereo with Contrastive Matching and Weighted Focal Loss
Learning-based multi-view stereo (MVS) methods have made impressive progress and surpassed traditional methods in recent years.
Simple Recurrent Neural Networks is all we need for clinical events predictions using EHR data
As a result, deep learning models developed for sequence modeling, like recurrent neural networks (RNNs) are common architecture for EHR-based clinical events predictive models.
Discover the Unknown Biased Attribute of an Image Classifier
To help human experts better find the AI algorithms' biases, we study a new problem in this work -- for a classifier that predicts a target attribute of the input image, discover its unknown biased attribute.
UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles
Human behavior understanding with unmanned aerial vehicles (UAVs) is of great significance for a wide range of applications, which simultaneously brings an urgent demand of large, challenging, and comprehensive benchmarks for the development and evaluation of UAV-based models.
Actor-Action Video Classification CSC 249/449 Spring 2020 Challenge Report
This technical report summarizes submissions and compiles from Actor-Action video classification challenge held as a final project in CSC 249/449 Machine Vision course (Spring 2020) at University of Rochester
Graph Neural Network Based Coarse-Grained Mapping Prediction
The selection of coarse-grained (CG) mapping operators is a critical step for CG molecular dynamics (MD) simulation.
Wasserstein Distance guided Adversarial Imitation Learning with Reward Shape Exploration
The generative adversarial imitation learning (GAIL) has provided an adversarial learning framework for imitating expert policy from demonstrations in high-dimensional continuous tasks.
Learning a Weakly-Supervised Video Actor-Action Segmentation Model with a Wise Selection
Instead of blindly trusting quality-inconsistent PAs, WS^2 employs a learning-based selection to select effective PAs and a novel region integrity criterion as a stopping condition for weakly-supervised training.
Deep Grouping Model for Unified Perceptual Parsing
The perceptual-based grouping process produces a hierarchical and compositional image representation that helps both human and machine vision systems recognize heterogeneous visual concepts.
Early Prediction of 30-day ICU Re-admissions Using Natural Language Processing and Machine Learning
ICU readmission is associated with longer hospitalization, mortality and adverse outcomes.
Cooperative Lane Changing via Deep Reinforcement Learning
In this paper, we study how to learn an appropriate lane changing strategy for autonomous vehicles by using deep reinforcement learning.
Lip Movements Generation at a Glance
In this paper, we consider a task of such: given an arbitrary audio speech and one lip image of arbitrary target identity, generate synthesized lip movements of the target identity saying the speech.
