Search Results for author:
Found 56 papers, 22 papers with code
Building Joint Relationship Attention Network for Image-Text Generation
Specifically, different from the previous relationship based approaches that only explore the single relationship in the image, our JRAN can effectively learn two relationships, the visual relationships among region features and the visual-semantic relationships between region features and semantic features, and further make a dynamic trade-off between them during outputting the relationship representation.
MMRL++: Parameter-Efficient and Interaction-Aware Representation Learning for Vision-Language Models
During training, both class and representation features are jointly optimized: a trainable projection layer is applied to representation tokens for task adaptation, while the projection layer for class token remains frozen to retain pre-trained knowledge.
Empowering AI to Generate Better AI Code: Guided Generation of Deep Learning Projects with LLMs
In this paper, we propose a novel planning-guided code generation method, DLCodeGen, tailored for generating deep learning projects.
AttentionRAG: Attention-Guided Context Pruning in Retrieval-Augmented Generation
The core idea of AttentionRAG lies in its attention focus mechanism, which reformulates RAG queries into a next-token prediction paradigm.
LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds
Animatable 3D human reconstruction from a single image is a challenging problem due to the ambiguity in decoupling geometry, appearance, and deformation.
MMRL: Multi-Modal Representation Learning for Vision-Language Models
For inference, a decoupling strategy is employed, wherein both representation and class features are utilized for base classes, while only the class features, which retain more generalized knowledge, are used for new tasks.
Ranked #2 on
Prompt Engineering
on ImageNet-A
LAM: Large Avatar Model for One-shot Animatable Gaussian Head
The centerpiece of our framework is the canonical Gaussian attributes generator, which utilizes FLAME canonical points as queries.
MCMat: Multiview-Consistent and Physically Accurate PBR Material Generation
In the generation stage, we adopt a Diffusion Transformer (DiT) model to generate PBR materials, where both the specially designed multi-branch DiT and reference-based DiT blocks adopt a global attention mechanism to promote feature interaction and fusion between different views, thereby improving multi-view consistency.
AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction
Generating animatable human avatars from a single image is essential for various digital human modeling applications.
MVImgNet2.0: A Larger-scale Dataset of Multi-view Images
This paper constructs the MVImgNet2. 0 dataset that expands MVImgNet into a total of ~520k objects and 515 categories, which derives a 3D dataset with a larger scale that is more comparable to ones in the 2D domain.
LLMs as Continuous Learners: Improving the Reproduction of Defective Code in Software Issues
Reproducing buggy code is the first and crucially important step in issue resolving, as it aids in identifying the underlying problems and validating that generated patches resolve the problem.
Just-In-Time Software Defect Prediction via Bi-modal Change Representation Learning
The prevailing approaches train models to represent code changes in history commits and utilize the learned representations to predict the presence of defects in the latest commit.
LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioning
For captioning, we finetune a large language model with the language-informative motion features to develop a strong motion captioning model.
CodeCipher: Learning to Obfuscate Source Code Against LLMs
CodeCipher transforms the LLM's embedding matrix so that each row corresponds to a different word in the original matrix, forming a token-to-token confusion mapping for obfuscating source code.
From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging
While large language models have made significant strides in code generation, the pass rate of the generated code is bottlenecked on subtle errors, often requiring human intervention to pass tests, especially for complex problems.
Ranked #18 on
Code Generation
on MBPP
MoGenTS: Motion Generation based on Spatial-Temporal Joint Modeling
Motion generation from discrete quantization offers many advantages over continuous regression, but at the cost of inevitable approximation errors.
Surface-Centric Modeling for High-Fidelity Generalizable Neural Surface Reconstruction
To this end, we propose SuRF, a new Surface-centric framework that incorporates a new Region sparsification based on a matching Field, achieving good trade-offs between performance, efficiency and scalability.
HIVE: HIerarchical Volume Encoding for Neural Implicit Surface Reconstruction
To better represent 3D shapes, we introduce a volume encoding to explicitly encode the spatial information.
StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal
The effectiveness of StableNormal is demonstrated through competitive performance in standard datasets such as DIODE-indoor, iBims, ScannetV2 and NYUv2, and also in various downstream tasks, such as surface reconstruction and normal enhancement.
GenS: Generalizable Neural Surface Reconstruction from Multi-View Images
Meanwhile, we introduce a multi-scale feature-metric consistency to impose the multi-view consistency in a more discriminative multi-scale feature space, which is robust to the failures of the photometric consistency.
An Optimization Framework to Enforce Multi-View Consistency for Texturing 3D Meshes
In particular, the third and fourth stages are iterated, with the cuts obtained in the fourth stage encouraging non-rigid alignment in the third stage to focus on regions close to the cuts.
VideoMV: Consistent Multi-View Generation Based on Large Video Generative Model
Images from video generative models are more suitable for multi-view generation because the underlying network architecture that generates them employs a temporal module to enforce frame consistency.
Between Lines of Code: Unraveling the Distinct Patterns of Machine and Human Programmers
Based on our findings, we propose DetectCodeGPT, a novel method for detecting machine-generated code, which improves DetectGPT by capturing the distinct stylized patterns of code.
JoAPR: Cleaning the Lens of Prompt Learning for Vision-Language Models
Our comprehensive experiments confirm that JoAPR substantially enhances the robustness of prompt learning for Vision-Language Models against label noise offering a promising direction for future research.
GPLD3D: Latent Diffusion of 3D Shape Generative Models by Enforcing Geometric and Physical Priors
The key to our approach is a new diffusion procedure that combines the discrete empirical data distribution and a continuous distribution induced by the quality checker.
RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D
Lifting 2D diffusion for 3D generation is a challenging problem due to the lack of geometric prior and the complex entanglement of materials and lighting in natural images.
InfeRE: Step-by-Step Regex Generation via Chain of Inference
Particularly, InfeRE outperforms the popular tree-based generation approach by 18. 1% and 11. 3% on both datasets, respectively, in terms of DFA@5 accuracy.
Knowledge Distillation from Single to Multi Labels: an Empirical Study
Knowledge distillation (KD) has been extensively studied in single-label image classification.
3D Former: Monocular Scene Reconstruction with 3D SDF Transformers
In this work, we propose an SDF transformer network, which replaces the role of 3D CNN for better 3D feature aggregation.
Dense RGB SLAM with Neural Implicit Maps
To reach this challenging goal without depth input, we introduce a hierarchical feature volume to facilitate the implicit map decoder.
Influential Recommender System
Traditional recommender systems are typically passive in that they try to adapt their recommendations to the user's historical interests.
Continuous Decomposition of Granularity for Neural Paraphrase Generation
While Transformers have had significant success in paragraph generation, they treat sentences as linear sequences of tokens and often neglect their hierarchical information.
Vision-Language Matching for Text-to-Image Synthesis via Generative Adversarial Networks
To address this issue, we propose a novel Vision-Language Matching strategy for text-to-image synthesis, named VLMGAN*, which introduces a dual vision-language matching mechanism to strengthen the image quality and semantic consistency.
A Unified Two-Stage Group Semantics Propagation and Contrastive Learning Network for Co-Saliency Detection
With the design of negative samples, the noise objects are suppressed.
Contrastive Cross-Modal Knowledge Sharing Pre-training for Vision-Language Representation Learning and Retrieval
Concretely, the first module is a weight-sharing transformer that builds on the head of the visual and textual encoders, aiming to semantically align text and image.
RCP: Recurrent Closest Point for Scene Flow Estimation on 3D Point Clouds
In the experiments, we evaluate the proposed method on both the 3D scene flow estimation and the point cloud registration task.
UTC: A Unified Transformer with Inter-Task Contrastive Learning for Visual Dialog
In this paper, we propose a contrastive learning-based framework UTC to unify and facilitate both discriminative and generative tasks in visual dialog with a single model.
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation
While recent works design increasingly complicated and powerful networks to directly regress the depth map, we take the path of CRFs optimization.
Ranked #1 on
Depth Prediction
on Matterport3D
Neural Window Fully-Connected CRFs for Monocular Depth Estimation
Estimating the accurate depth from a single image is challenging since it is inherently ambiguous and ill-posed.
RCP: Recurrent Closest Point for Point Cloud
In the experiments, we evaluate the proposed method on both the 3D scene flow estimation and the point cloud registration task.
Response Generation with Context-Aware Prompt Learning
Pre-trained language models (PLM) have marked a huge leap in neural dialogue modeling.
DRO: Deep Recurrent Optimizer for Video to Depth
There are increasing interests of studying the video-to-depth (V2D) problem with machine learning techniques.
DialogBERT: Discourse-Aware Response Generation via Learning to Recover and Rank Utterances
Recent advances in pre-trained language models have significantly improved neural response generation.
Learning Dual Semantic Relations with Graph Attention for Image-Text Matching
Thus, a novel multi-level semantic relations enhancement approach named Dual Semantic Relations Attention Network(DSRAN) is proposed which mainly consists of two modules, separate semantic relations module and the joint semantic relations module.
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
The deep multi-view stereo (MVS) and stereo matching approaches generally construct 3D cost volumes to regularize and regress the output depth or disparity.
Ranked #13 on
Point Clouds
on Tanks and Temples
Landmark Assisted CycleGAN for Cartoon Face Generation
In this paper, we are interested in generating an cartoon face of a person by using unpaired training data between real faces and cartoon ones.
Attribute-Driven Spontaneous Motion in Unpaired Image Translation
Current image translation methods, albeit effective to produce high-quality results in various applications, still do not consider much geometric transform.
Multiple Encoder-Decoders Net for Lane Detection
For semantic image segmentation and lane detection, nets with a single spatial pyramid structure or encoder-decoder structure are usually exploited.
Batch DropBlock Network for Person Re-identification and Beyond
In this paper, we propose the Batch DropBlock (BDB) Network which is a two branch network composed of a conventional ResNet-50 as the global branch and a feature dropping branch.
Ranked #8 on
Person Re-Identification
on Market-1501-C
DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder
Variational autoencoders~(VAEs) have shown a promise in data-driven conversation modeling.
DeepAM: Migrate APIs with Multi-modal Sequence to Sequence Learning
They rely on the sparse availability of bilingual projects, thus producing a limited number of API mappings.
Deep API Learning
We propose DeepAPI, a deep learning based approach to generate API usage sequences for a given natural language query.
Max-Pooling Dropout for Regularization of Convolutional Neural Networks
Recently, dropout has seen increasing use in deep learning.
Towards Dropout Training for Convolutional Neural Networks
However, its effect in convolutional and pooling layers is still not clear.
Aspect-based Opinion Summarization with Convolutional Neural Networks
To tackle aspect mapping and sentiment classification, we propose two Convolutional Neural Network (CNN) based methods, cascaded CNN and multitask CNN.
