Search Results for author:
Found 49 papers, 25 papers with code
Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback
In this work, we make the first attempt to fine-tune all-modality models (i. e. input and output with any modality, also named any-to-any models) using human preference data across all modalities (including text, image, audio, and video), ensuring its behavior aligns with human intentions.
SEAGraph: Unveiling the Whole Story of Paper Review Comments
Peer review, as a cornerstone of scientific research, ensures the integrity and quality of scholarly work by providing authors with objective feedback for refinement.
Domain Adaptive Diabetic Retinopathy Grading with Model Absence and Flowing Data
Specifically, we first theoretically reformulate conventional perturbation optimization in a generative way--learning a perturbation generation function with a latent input variable.
Implicit neural representation for free-breathing MR fingerprinting (INR-MRF): co-registered 3D whole-liver water T1, water T2, proton density fat fraction, and R2* mapping
Purpose: To develop an MRI technique for free-breathing 3D whole-liver quantification of water T1, water T2, proton density fat fraction (PDFF), R2*.
Self-Supervised Contrastive Graph Clustering Network via Structural Information Fusion
Graph clustering, a classical task in graph learning, involves partitioning the nodes of a graph into distinct clusters.
Deep learning improved autofocus for motion artifact reduction and its application in quantitative susceptibility mapping
Purpose: To develop a pipeline for motion artifact correction in mGRE and quantitative susceptibility mapping (QSM).
Feature-Adaptive and Data-Scalable In-Context Learning
In this paper, we propose a feature-adaptive and data-scalable in-context learning framework (FADS-ICL), which can leverage task-adaptive features to promote inference on the downstream task, with the supervision of beyond-context samples.
Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
For fine-grained language understanding, we train a Multimodal Large Language Model to refine the captions of the images.
Iterative Experience Refinement of Software-Developing Agents
We propose two fundamental patterns: the successive pattern, refining based on nearest experiences within a task batch, and the cumulative pattern, acquiring experiences across all previous task batches.
Uncertainty-Aware Deep Video Compression with Ensembles
Deep learning-based video compression is a challenging task, and many previous state-of-the-art learning-based video codecs use optical flows to exploit the temporal correlation between successive frames and then compress the residual error.
Neural Video Compression with Feature Modulation
This results in a better learning of the quantization scaler and helps our NVC support about 11. 4 dB PSNR range.
Generative Latent Coding for Ultra-Low Bitrate Image Compression
To address this issue we introduce a Generative Latent Coding (GLC) architecture which performs transform coding in the latent space of a generative vector-quantized variational auto-encoder (VQ-VAE) instead of in the pixel space.
Implicit Motion Function
Recent advancements in video modeling extensively rely on optical flow to represent the relationships across frames but this approach often lacks efficiency and fails to model the probability of the intrinsic motion of objects.
Hierarchical Intra-modal Correlation Learning for Label-free 3D Semantic Segmentation
Recent methods for label-free 3D semantic segmentation aim to assist 3D model training by leveraging the open-world recognition ability of pre-trained vision language models.
Experiential Co-Learning of Software-Developing Agents
Recent advancements in large language models (LLMs) have brought significant changes to various domains, especially through LLM-driven autonomous agents.
Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning
To this end, we introduce Carve3D, an improved RLFT algorithm coupled with a novel Multi-view Reconstruction Consistency (MRC) metric, to enhance the consistency of multi-view diffusion models.
Grammatical Error Correction via Mixed-Grained Weighted Training
In this paper, the inherent discrepancies are manifested in two aspects, namely, accuracy of data annotation and diversity of potential annotations.
DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Model
We propose \textbf{DMV3D}, a novel 3D generation approach that uses a transformer-based 3D large reconstruction model to denoise multi-view diffusion.
Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model
Text-to-3D with diffusion models has achieved remarkable progress in recent years.
JOTR: 3D Joint Contrastive Learning with Transformers for Occluded Human Mesh Recovery
Our method includes an encoder-decoder transformer architecture to fuse 2D and 3D representations for achieving 2D$\&$3D aligned results in a coarse-to-fine manner and a novel 3D joint contrastive learning approach for adding explicitly global supervision for the 3D feature space.
ChatDev: Communicative Agents for Software Development
Numerous studies used deep learning to improve specific phases in a waterfall model, such as design, coding, and testing.
ZJU ReLER Submission for EPIC-KITCHEN Challenge 2023: TREK-150 Single Object Tracking
MSDeAOT efficiently propagates object masks from previous frames to the current frame using two feature scales of 16 and 8.
DAGrid: Directed Accumulator Grid
Specifically, the network incorporating DAGrid has realized a 70. 8% reduction in network parameter size and a 96. 8% decrease in FLOPs, while concurrently improving the Dice score for skin lesion segmentation by 1. 0% compared to state-of-the-art transformers.
Online Portfolio Management via Deep Reinforcement Learning with High-Frequency Data
In addition, while the vast majority of SOTA strategies maintain a poor turnover rate of approximately greater than 50% on average, our framework enjoys a relatively low turnover rate on all datasets, efficiency analysis illustrates that our framework no longer has the quadratic dependency limitation.
mcLARO: Multi-Contrast Learned Acquisition and Reconstruction Optimization for simultaneous quantitative multi-parametric mapping
Results: The retrospective ablation study showed improved image sharpness of mcLARO compared to the baseline network without multi-contrast sampling pattern optimization or image feature fusion, and negligible bias and narrow 95% limits of agreement on regional T1, T2, T2* and QSM values were obtained by the under-sampled reconstructions compared to the fully sampled reconstruction.
DeDA: Deep Directed Accumulator
Chronic active multiple sclerosis lesions, also termed as rim+ lesions, can be characterized by a hyperintense rim at the edge of the lesion on quantitative susceptibility maps.
Neural Video Compression with Diverse Contexts
Better yet, our codec has surpassed the under-developing next generation traditional codec/ECM in both RGB and YUV420 colorspaces, in terms of PSNR.
EVC: Towards Real-Time Neural Image Compression with Mask Decay
Both mask decay and residual representation learning greatly improve the RD performance of our scalable encoder.
Spatially Covariant Lesion Segmentation
Compared to natural images, medical images usually show stronger visual patterns and therefore this adds flexibility and elasticity to resource-limited clinical applications by injecting proper priors into neural networks.
Motion Information Propagation for Neural Video Compression
Meanwhile, besides assisting frame coding at the current time step, the feature from context generation will be propagated as motion condition when coding the subsequent motion latent.
VideoTrack: Learning To Track Objects via Video Transformer
Existing Siamese tracking methods, which are built on pair-wise matching between two single frames, heavily rely on additional sophisticated mechanism to exploit temporal information among successive video frames, hindering them from high efficiency and industrial deployments.
iEnhancer-ELM: improve enhancer identification by extracting position-related multiscale contextual information based on enhancer language models
Although many feature extraction methods have been proposed to improve the performance of enhancer identification, they cannot learn position-related multiscale contextual information from raw DNA sequences.
Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation
We propose to apply chain rule on the learned gradients, and back-propagate the score of a diffusion model through the Jacobian of a differentiable renderer, which we instantiate to be a voxel radiance field.
Ranked #6 on
Text to 3D
on T$^3$Bench
LARO: Learned Acquisition and Reconstruction Optimization to accelerate Quantitative Susceptibility Mapping
In this paper, we present our new framework, called Learned Acquisition and Reconstruction Optimization (LARO), which aims to accelerate the multi-echo gradient echo (mGRE) pulse sequence for QSM.
Improving Chinese Spelling Check by Character Pronunciation Prediction: The Effects of Adaptivity and Granularity
In this paper, we consider introducing an auxiliary task of Chinese pronunciation prediction (CPP) to improve CSC, and, for the first time, systematically discuss the adaptivity and granularity of this auxiliary task.
Hybrid Spatial-Temporal Entropy Modelling for Neural Video Compression
Besides estimating the probability distribution, our entropy model also generates the quantization step at spatial-channel-wise.
Adapting CLIP For Phrase Localization Without Further Training
Our method for phrase localization requires no human annotations or additional training.
Neural Compression-Based Feature Learning for Video Restoration
The temporal features usually contain various noisy and uncorrelated information, and they may interfere with the restoration of the current frame.
Temporal Context Mining for Learned Video Compression
From the stored propagated features, we propose to learn multi-scale temporal contexts, and re-fill the learned temporal contexts into the modules of our compression scheme, including the contextual encoder-decoder, the frame generator, and the temporal context encoder.
User Based Design and Evaluation Pipeline for Indoor Airships
Designing a controllable airship for non-expert users or preemptively evaluating the performance of desired airships has always been a very challenging problem.
Deep Contextual Video Compression
In this paper, we propose a deep contextual video compression framework to enable a paradigm shift from predictive coding to conditional coding.
Curvy: An Interactive Design Tool for Varying Density Support Structures
Combined with the build orientation optimization, Curvy provides a practical solution to the design of support structures with minimal perceptual or functional impact on the target part to be printed.
Graphics Computational Geometry
Separable Structure Modeling for Semi-supervised Video Object Segmentation
Specifically, we first compute a pixel-wise similarity matrix by using representations of reference and target pixels and then select top-rank reference pixels for target pixel classification.
STS-GAN: Can We Synthesize Solid Texture with High Fidelity from Arbitrary 2D Exemplar?
Solid texture synthesis (STS), an effective way to extend a 2D exemplar to a 3D solid volume, exhibits advantages in computational photography.
DSNet: A Flexible Detect-to-Summarize Network for Video Summarization
In this paper, we propose a Detect-to-Summarize network (DSNet) framework for supervised video summarization.
Ranked #2 on
Video Summarization
on TvSum
(using extra training data)
Adaptive Generation Model: A New Ensemble Method
As a common method in Machine Learning, Ensemble Method is used to train multiple models from a data set and obtain better results through certain combination strategies.
Iterative Distance-Aware Similarity Matrix Convolution with Mutual-Supervised Point Elimination for Efficient Point Cloud Registration
In this paper, we propose a novel learning-based pipeline for partially overlapping 3D point cloud registration.
Constructing Financial Sentimental Factors in Chinese Market Using Natural Language Processing
Especially during the Chinese market crash in 2015, the Pearson correlation coefficient of adjusted sentimental factor with SSE is 0. 5844, which suggests that our model can provide a solid guidance, especially in the special period when the market is influenced greatly by public sentiment.
