Search Results for author:
Found 35 papers, 11 papers with code
Learning Temporal Cues by Predicting Objects Move for Multi-camera 3D Object Detection
To this end, we propose a model called DAP (Detection After Prediction), consisting of a two-branch network: (i) a branch responsible for forecasting the current objects' poses given past observations and (ii) another branch that detects objects based on the current and past observations.
Just Add $100 More: Augmenting NeRF-based Pseudo-LiDAR Point Cloud for Resolving Class-imbalance Problem
Typical LiDAR-based 3D object detection models are trained in a supervised manner with real-world data collection, which is often imbalanced over classes (or long-tailed).
CMDA: Cross-Modal and Domain Adversarial Adaptation for LiDAR-Based 3D Object Detection
Recent LiDAR-based 3D Object Detection (3DOD) methods show promising results, but they often do not generalize well to target domains outside the source (or training) data distribution.
Mitigating the Linguistic Gap with Phonemic Representations for Robust Multilingual Language Understanding
Approaches to improving multilingual language understanding often require multiple languages during the training phase, rely on complicated training techniques, and -- importantly -- struggle with significant performance gaps between high-resource and low-resource languages.
Relaxed Contrastive Learning for Federated Learning
We propose a novel contrastive learning framework to effectively address the challenges of data heterogeneity in federated learning.
MTVG : Multi-text Video Generation with Text-to-Video Models
Concerning the characteristics of video, multi-text conditioning incorporating sequential events is necessary for next-step video generation.
InstructBooth: Instruction-following Personalized Text-to-Image Generation
In this work, we introduce InstructBooth, a novel method designed to enhance image-text alignment in personalized text-to-image models without sacrificing the personalization ability.
Clustering-based Image-Text Graph Matching for Domain Generalization
However, they use pivot embedding in global manner (i. e., aligning an image embedding with sentence-level text embedding), not fully utilizing the semantic cues of given text description.
The Power of Sound (TPoS): Audio Reactive Video Generation with Stable Diffusion
Hence, we propose The Power of Sound (TPoS) model to incorporate audio input that includes both changeable temporal semantics and magnitude.
Soundini: Sound-Guided Diffusion for Natural Video Editing
We propose a method for adding sound-guided visual effects to specific regions of videos with a zero-shot setting.
FPANet: Frequency-based Video Demoireing using Frame-level Post Alignment
Interference between overlapping gird patterns creates moire patterns, degrading the visual quality of an image that captures a screen of a digital display device by an ordinary digital camera.
Ensuring Visual Commonsense Morality for Text-to-Image Generation
Text-to-image generation methods produce high-resolution and high-quality images, but these methods should not produce immoral images that may contain inappropriate content from the perspective of commonsense morality.
LISA: Localized Image Stylization with Audio via Implicit Neural Representation
We present a novel framework, Localized Image Stylization with Audio (LISA) which performs audio-driven localized image stylization.
Zero-shot Visual Commonsense Immorality Prediction
Here, we propose a model that predicts visual commonsense immorality in a zero-shot manner.
Resolving Class Imbalance for LiDAR-based Object Detector by Dynamic Weight Average and Contextual Ground Truth Sampling
An autonomous driving system requires a 3D object detector, which must perceive all present road agents reliably to navigate an environment safely.
Robust Sound-Guided Image Manipulation
Our extensive experiments show that our sound-guided image manipulation approach produces semantically and visually more plausible manipulation results than the state-of-the-art text and sound-guided image manipulation methods, which are further confirmed by our human evaluations.
Grounding Visual Representations with Texts for Domain Generalization
In this work, we advocate for leveraging natural language supervision for the domain generalization task.
Multi-Level Branched Regularization for Federated Learning
A critical challenge of federated learning is data heterogeneity and imbalance across clients, which leads to inconsistency between local networks and unstable convergence of global models.
An Embedding-Dynamic Approach to Self-supervised Learning
It also uses a purely-dynamic local dispersive force (Brownian motion) that shows improved performance over other methods and does not require knowledge of other particle coordinates.
ORA3D: Overlap Region Aware Multi-view 3D Object Detection
Current multi-view 3D object detection methods often fail to detect objects in the overlap region properly, and the networks' understanding of the scene is often limited to that of a monocular detection network.
Ranked #6 on
Robust Camera Only 3D Object Detection
on nuScenes-C
StopNet: Scalable Trajectory and Occupancy Prediction for Urban Autonomous Driving
A whole-scene sparse input representation allows StopNet to scale to predicting trajectories for hundreds of road agents with reliable latency.
Sound-Guided Semantic Video Generation
The recent success in StyleGAN demonstrates that pre-trained StyleGAN latent space is useful for realistic video generation.
Occupancy Flow Fields for Motion Forecasting in Autonomous Driving
We propose Occupancy Flow Fields, a new representation for motion forecasting of multiple agents, an important task in autonomous driving.
Communication-Efficient Federated Learning with Accelerated Client Gradient
To address this challenge, we propose a simple but effective federated learning framework, which improves the consistency across clients and facilitates the convergence of the server model.
Sound-Guided Semantic Image Manipulation
Our audio encoder is trained to produce a latent representation from an audio input, which is forced to be aligned with image and text representations in the multi-modal embedding space.
A Scenario-Based Platform for Testing Autonomous Vehicle Behavior Prediction Models in Simulation
Hence, it is important that these prediction models are extensively tested in various test scenarios involving interactive behaviors prior to deployment.
SelfReg: Self-supervised Contrastive Regularization for Domain Generalization
However, the performance of contrastive learning fundamentally depends on quality and quantity of negative data pairs.
Ranked #58 on
Domain Generalization
on PACS
Advisable Learning for Self-Driving Vehicles by Internalizing Observation-to-Action Rules
Humans learn to drive through both practice and theory, e. g. by studying the rules, while most self-driving systems are limited to the former.
Attentional Bottleneck: Towards an Interpretable Deep Driving Network
Deep neural networks are a key component of behavior prediction and motion generation for self-driving cars.
Grounding Human-to-Vehicle Advice for Self-driving Vehicles
We show that taking advice improves the performance of the end-to-end network, while the network cues on a variety of visual features that are provided by advice.
HATS: A Hierarchical Graph Attention Network for Stock Movement Prediction
Methods that use relational data for stock market prediction have been recently proposed, but they are still in their infancy.
Periphery-Fovea Multi-Resolution Driving Model guided by Human Attention
Inspired by human vision, we propose a new periphery-fovea multi-resolution driving model that predicts vehicle speed from dash camera videos.
Textual Explanations for Self-Driving Vehicles
Finally, we explore a version of our model that generates rationalizations, and compare with introspective explanations on the same video segments.
Predicting Driver Attention in Critical Situations
Because critical driving moments are so rare, collecting enough data for these situations is difficult with the conventional in-car data collection protocol---tracking eye movements during driving.
Interpretable Learning for Self-Driving Cars by Visualizing Causal Attention
The attention model highlights image regions that potentially influence the network's output.
