Search Results for author:
Found 29 papers, 10 papers with code
One-Minute Video Generation with Test-Time Training
We have only experimented with one-minute videos due to resource constraints, but the approach can be extended to longer videos and more complex stories.
M3Net: Multimodal Multi-task Learning for 3D Detection, Segmentation, and Occupancy Prediction in Autonomous Driving
In this paper, we introduce M3Net, a novel multimodal and multi-task network that simultaneously tackles detection, segmentation, and 3D occupancy prediction for autonomous driving and achieves superior performance than single task model.
Parallel Sequence Modeling via Generalized Spatial Propagation Network
We present the Generalized Spatial Propagation Network (GSPN), a new attention mechanism optimized for vision tasks that inherently captures 2D spatial structures.
GaussianMarker: Uncertainty-Aware Copyright Protection of 3D Gaussian Splatting
3D Gaussian Splatting (3DGS) has become a crucial method for acquiring 3D assets.
Geometry Cloak: Preventing TGS-based 3D Reconstruction from Copyrighted Images
Single-view 3D reconstruction methods like Triplane Gaussian Splatting (TGS) have enabled high-quality 3D model generation from just a single image input within seconds.
GeometrySticker: Enabling Ownership Claim of Recolorized Neural Radiance Fields
While approaches like CopyRNeRF have been introduced to embed binary messages into NeRF models as digital signatures for copyright protection, the process of recolorization can remove these binary messages.
TCM-FTP: Fine-Tuning Large Language Models for Herbal Prescription Prediction
However, this task faces limitations due to the scarcity of high-quality clinical datasets and the complex relationship between symptoms and herbs.
Protecting NeRFs' Copyright via Plug-And-Play Watermarking Base Model
Neural Radiance Fields (NeRFs) have become a key method for 3D scene representation.
Unlocking Continual Learning Abilities in Language Models
To address this limitation, we introduce $\textbf{MIGU}$ ($\textbf{M}$agn$\textbf{I}$tude-based $\textbf{G}$radient $\textbf{U}$pdating for continual learning), a rehearsal-free and task-label-free method that only updates the model parameters with large magnitudes of output in LMs' linear layers.
RegionGPT: Towards Region Understanding Vision Language Model
Vision language models (VLMs) have experienced rapid advancements through the integration of large language models (LLMs) with image-text pairs, yet they struggle with detailed regional visual understanding due to limited spatial awareness of the vision encoder, and the use of coarse-grained training data that lacks detailed, region-specific captions.
Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling
For the first stage, we propose a diffusion-based motion field predictor, which focuses on deducing the trajectories of the reference image's pixels.
Resilient Practical Test-Time Adaptation: Soft Batch Normalization Alignment and Entropy-driven Memory Bank
Test-time domain adaptation effectively adjusts the source domain model to accommodate unseen domain shifts in a target domain during inference.
AHIVE: Anatomy-aware Hierarchical Vision Encoding for Interactive Radiology Report Retrieval
Automatic radiology report generation using deep learning models has been recently explored and found promising.
CopyRNeRF: Protecting the CopyRight of Neural Radiance Fields
Neural Radiance Fields (NeRF) have the potential to be a major representation of media.
TrajectoryFormer: 3D Object Tracking Transformer with Predictive Trajectory Hypotheses
3D multi-object tracking (MOT) is vital for many applications including autonomous driving vehicles and service robots.
VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation
We first propose a TRi-frame Optical Flow (TROF) module that estimates bi-directional optical flows for the center frame in a three-frame manner.
FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation
FlowFormer introduces a transformer architecture into optical flow estimation and achieves state-of-the-art performance.
SVD-PINNs: Transfer Learning of Physics-Informed Neural Networks via Singular Value Decomposition
Physics-informed neural networks (PINNs) have attracted significant attention for solving partial differential equations (PDEs) in recent years because they alleviate the curse of dimensionality that appears in traditional methods.
Adaptive Label Smoothing with Self-Knowledge in Natural Language Generation
Furthermore, inspired by recent work in bridging label smoothing and knowledge distillation, our work utilizes self-knowledge as a prior label distribution in softening target labels, and presents theoretical support for the regularization effect by knowledge distillation and the dynamic smoothing parameter.
Hard Gate Knowledge Distillation -- Leverage Calibration for Robust and Reliable Language Model
The question is answered in our work with the concept of model calibration; we view a teacher model not only as a source of knowledge but also as a gauge to detect miscalibration of a student.
NeuralMarker: A Framework for Learning General Marker Correspondence
We tackle the problem of estimating correspondences from a general marker, such as a movie poster, to an image that captures such a marker.
Learning Degradation Representations for Image Deblurring
With the integration, MSDI-Net can handle various and complicated blurry patterns adaptively.
Ranked #23 on
Image Deblurring
on GoPro
A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shift
In this study, we propose a simple yet effective framework for video restoration.
Ranked #2 on
Deblurring
on GoPro
(using extra training data)
MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection
Accurate and reliable 3D detection is vital for many applications including autonomous driving vehicles and service robots.
FlowFormer: A Transformer Architecture for Optical Flow
We introduce optical Flow transFormer, dubbed as FlowFormer, a transformer-based neural network architecture for learning optical flow.
Ranked #4 on
Optical Flow Estimation
on KITTI 2015 (train)
Adaptive Label Smoothing with Self-Knowledge
Overconfidence has been shown to impair generalization and calibration of a neural network.
Self-distillation with Batch Knowledge Ensembling Improves ImageNet Classification
In this way, our BAKE framework achieves online knowledge ensembling across multiple samples with only a single network.
LIFE: Lighting Invariant Flow Estimation
However, local image contents are inevitably ambiguous and error-prone during the cross-image feature matching process, which hinders downstream tasks.
Understanding Top-k Sparsification in Distributed Deep Learning
Distributed stochastic gradient descent (SGD) algorithms are widely deployed in training large-scale deep learning models, while the communication overhead among workers becomes the new system bottleneck.
