Search Results for author:
Found 29 papers, 9 papers with code
CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility
To this end, this paper proposes a novel text-guided video inpainting model that achieves better consistency, controllability and compatibility.
AcademicGPT: Empowering Academic Research
Our training corpus mainly consists of academic papers, thesis, content from some academic domain, high-quality Chinese data and others.
TOSS:High-quality Text-guided Novel View Synthesis from a Single Image
In this paper, we present TOSS, which introduces text to the task of novel view synthesis (NVS) from just a single RGB image.
Delta-LoRA: Fine-Tuning High-Rank Parameters with the Delta of Low-Rank Matrices
In this paper, we present Delta-LoRA, which is a novel parameter-efficient approach to fine-tune large language models (LLMs).
DreamTime: An Improved Optimization Strategy for Text-to-3D Content Creation
Text-to-image diffusion models pre-trained on billions of image-text pairs have recently enabled text-to-3D content creation by optimizing a randomly initialized Neural Radiance Fields (NeRF) with score distillation.
Understanding Optimization of Deep Learning via Jacobian Matrix and Lipschitz Constant
This article provides a comprehensive understanding of optimization in deep learning, with a primary focus on the challenges of gradient vanishing and gradient exploding, which normally lead to diminished model representational ability and training instability, respectively.
detrex: Benchmarking Detection Transformers
To address this issue, we develop a unified, highly modular, and lightweight codebase called detrex, which supports a majority of the mainstream DETR-based instance recognition algorithms, covering various fundamental tasks, including object detection, segmentation, and pose estimation.
LipsFormer: Introducing Lipschitz Continuity to Vision Transformers
In contrast to previous practical tricks that address training instability by learning rate warmup, layer normalization, attention formulation, and weight initialization, we show that Lipschitz continuity is a more essential property to ensure training stability.
DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP Training
In this way, we can reduce the GPU memory consumption of contrastive loss computation from $\bigO(B^2)$ to $\bigO(\frac{B^2}{N})$, where $B$ and $N$ are the batch size and the number of GPUs used for training.
Exploring Vision Transformers as Diffusion Learners
We further provide a hypothesis on the implication of disentangling the generative backbone as an encoder-decoder structure and show proof-of-concept experiments verifying the effectiveness of a stronger encoder for generative tasks with ASymmetriC ENcoder Decoder (ASCEND).
DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR
We present in this paper a novel query formulation using dynamic anchor boxes for DETR (DEtection TRansformer) and offer a deeper understanding of the role of queries in DETR.
Ranked #11 on
2D Object Detection
on SARDet-100K
1st Place Solution for ICDAR 2021 Competition on Mathematical Formula Detection
In this technical report, we present our 1st place solution for the ICDAR 2021 competition on mathematical formula detection (MFD).
Winner Team Mia at TextVQA Challenge 2021: Vision-and-Language Representation Learning with Pre-trained Sequence-to-Sequence Model
TextVQA requires models to read and reason about text in images to answer questions about them.
PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Table Image Recognition to Latex
This paper presents our solution for the ICDAR 2021 Competition on Scientific Table Image Recognition to LaTeX.
PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Literature Parsing Task B: Table Recognition to HTML
In our method, we divide the table content recognition task into foursub-tasks: table structure recognition, text line detection, text line recognition, and box assignment. Our table structure recognition algorithm is customized based on MASTER [1], a robust image textrecognition algorithm.
Ranked #1 on
Table Recognition
on PubTabNet
Learning Graph Normalization for Graph Neural Networks
We conduct extensive experiments on benchmark datasets for different tasks, including node classification, link prediction, graph classification and graph regression, and confirm that the learned graph normalization leads to competitive results and that the learned weights suggest the appropriate normalization techniques for the specific task.
Hamming OCR: A Locality Sensitive Hashing Neural Network for Scene Text Recognition
Thus, we propose a lightweight scene text recognition model named Hamming OCR.
PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks
Computer vision with state-of-the-art deep learning models has achieved huge success in the field of Optical Character Recognition (OCR) including text detection and recognition tasks recently.
Neural Mesh Refiner for 6-DoF Pose Estimation
We utilise the overlay between the accurate mask prediction and less accurate mesh prediction to iteratively optimise the direct regressed 6D pose information with a focus on translation estimation.
MASTER: Multi-Aspect Non-local Network for Scene Text Recognition
Attention-based scene text recognizers have gained huge success, which leverages a more compact intermediate representation to learn 1d- or 2d- attention by a RNN-based encoder-decoder architecture.
Self-Supervised Convolutional Subspace Clustering Network
However, the applicability of subspace clustering has been limited because practical visual data in raw form do not necessarily lie in such linear subspaces.
Ranked #2 on
Image Clustering
on Extended Yale-B
Homocentric Hypersphere Feature Embedding for Person Re-identification
Person re-identification (Person ReID) is a challenging task due to the large variations in camera viewpoint, lighting, resolution, and human pose.
Face Recognition via Centralized Coordinate Learning
Owe to the rapid development of deep neural network (DNN) techniques and the emergence of large scale face databases, face recognition has achieved a great success in recent years.
3D Surface Detail Enhancement From a Single Normal Map
In 3D reconstruction, the obtained surface details are mainly limited to the visual sensor due to sampling and quantization in the digitalization process.
Probing the Intra-Component Correlations within Fisher Vector for Material Classification
Fisher vector (FV) has become a popular image representation.
HEp-2 Cell Classification: The Role of Gaussian Scale Space Theory as A Pre-processing Approach
We validate the GSS pre-processing under the Local Binary Pattern (LBP) and the Bag-of-Words (BoW) frameworks.
LOAD: Local Orientation Adaptive Descriptor for Texture and Material Classification
It is worth to mention that we achieve a 65. 4\% classification accuracy-- which is, to the best of our knowledge, the highest record by far --on Flickr Material Database by using a single feature.
HEp-2 Cell Classification via Fusing Texture and Shape Information
Indirect Immunofluorescence (IIF) HEp-2 cell image is an effective evidence for diagnosis of autoimmune diseases.
Dynamic texture and scene classification by transferring deep image features
Moreover we explore two different implementations of the TCoF scheme, i. e., the \textit{spatial} TCoF and the \textit{temporal} TCoF, in which the mean-removed frames and the difference between two adjacent frames are used as the inputs of the ConvNet, respectively.
