Search Results for author:
Found 53 papers, 25 papers with code
OnlineVPO: Align Video Diffusion Model with Online Video-Centric Preference Optimization
To tackle these issues, we introduce OnlineVPO, a more efficient preference learning approach tailored specifically for video diffusion models.
Prompt-A-Video: Prompt Your Video Diffusion Model via Preference-Aligned LLM
Text-to-video models have made remarkable advancements through optimization on high-quality text-video pairs, where the textual prompts play a pivotal role in determining quality of output videos.
Fast Prompt Alignment for Text-to-Image Generation
Text-to-image generation has advanced rapidly, yet aligning complex textual prompts with generated visuals remains challenging, especially with intricate object relationships and fine-grained details.
SeedEdit: Align Image Re-Generation to Image Editing
We introduce SeedEdit, a diffusion model that is able to revise a given image with any text prompt.
Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Large Models
Vision-Language Large Models (VLMs) recently become primary backbone of AI, due to the impressive performance.
UniFL: Improve Latent Diffusion Model via Unified Feedback Learning
Latent diffusion models (LDM) have revolutionized text-to-image generation, leading to the proliferation of various advanced models and diverse downstream applications.
Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Models
Vision-Language Large Models (VLMs) have become primary backbone of AI, due to the impressive performance.
Enhancing Cross-domain Click-Through Rate Prediction via Explicit Feature Augmentation
Later the augmentation network employs the explicit cross-domain knowledge as augmented information to boost the target domain CTR prediction.
Forgedit: Text Guided Image Editing via Learning and Forgetting
Text-guided image editing on real or synthetic images, given only the original image itself and the target text prompt as inputs, is a very general and challenging task.
Category-Oriented Representation Learning for Image to Multi-Modal Retrieval
We focus on representation learning for IMMR and analyze three key challenges for it: 1) skewed data and noisy label in real-world industrial data, 2) the information-inequality between image and text modality of documents when learning representations, 3) effective and efficient training in large-scale industrial contexts.
Cross-domain Augmentation Networks for Click-Through Rate Prediction
The translation network is able to compute features from two domains with heterogeneous inputs separately by designing two independent branches, and then learn meaningful cross-domain knowledge using a designed cross-supervised feature translator.
Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Grounding
The sampling module aims to select these informative patches by predicting the offsets with respect to a reference point, while the decoding module works for extracting the grounded object information by performing cross attention between image features and text features.
Cross-Architecture Self-supervised Video Representation Learning
In this paper, we present a new cross-architecture contrastive learning (CACL) framework for self-supervised video representation learning.
InsCLR: Improving Instance Retrieval with Self-Supervision
This work aims at improving instance retrieval with self-supervision.
End-to-End Dense Video Grounding via Parallel Regression
In this paper, we tackle a new problem of dense video grounding, by simultaneously localizing multiple moments with a paragraph as input.
TOOD: Task-aligned One-stage Object Detection
One-stage object detection is commonly implemented by optimizing two sub-tasks: object classification and localization, using heads with two parallel branches, which might lead to a certain level of spatial misalignment in predictions between the two tasks.
Ranked #3 on
2D Object Detection
on CeyMo
Exploring Classification Equilibrium in Long-Tailed Object Detection
Specifically, EBL increases the intensity of the adjustment of the decision boundary for the weak classes by a designed score-guided loss margin between any two classes.
Ranked #12 on
Object Detection
on LVIS v1.0 val
Mutually-aware Sub-Graphs Differentiable Architecture Search
In this paper, we propose a conceptually simple yet efficient method to bridge these two paradigms, referred as Mutually-aware Sub-Graphs Differentiable Architecture Search (MSG-DAS).
Brain Image Synthesis With Unsupervised Multivariate Canonical CSCl4Net
Recent advances in neuroscience have highlighted the effectiveness of multi-modal medical data for investigating certain pathologies and understanding human cognition.
Rethinking Deep Contrastive Learning with Embedding Memory
Pair-wise loss functions have been extensively studied and shown to continuously improve the performance of deep metric learning (DML).
Brain Image Synthesis with Unsupervised Multivariate Canonical CSC$\ell_4$Net
Recent advances in neuroscience have highlighted the effectiveness of multi-modal medical data for investigating certain pathologies and understanding human cognition.
Unchain the Search Space with Hierarchical Differentiable Architecture Search
To overcome this limitation, in this paper, we propose a Hierarchical Differentiable Architecture Search (H-DAS) that performs architecture search both at the cell level and at the stage level.
Representation Sharing for Fast Object Detector Search and Beyond
FAD consists of a designed search space and an efficient architecture search algorithm.
V4D: 4D Convolutional Neural Networks for Video-level Representation Learning
Most existing 3D CNN structures for video representation learning are clip-based methods, and do not consider video-level temporal evolution of spatio-temporal features.
Deformable Siamese Attention Networks for Visual Object Tracking
In this paper, we propose Deformable Siamese Attention Networks, referred to as SiamAttn, by introducing a new Siamese attention mechanism that computes deformable self-attention and cross-attention.
Channel Interaction Networks for Fine-Grained Image Categorization
Fine-grained image categorization is challenging due to the subtle inter-class differences. We posit that exploiting the rich relationships between channels can help capture such differences since different channels correspond to different semantics.
Ranked #26 on
Fine-Grained Image Classification
on FGVC Aircraft
iFAN: Image-Instance Full Alignment Networks for Adaptive Object Detection
We propose Image-Instance Full Alignment Networks (iFAN) to tackle this problem by precisely aligning feature distributions on both image and instance levels: 1) Image-level alignment: multi-scale features are roughly aligned by training adversarial domain classifiers in a hierarchically-nested fashion.
V4D:4D Convolutional Neural Networks for Video-level Representation Learning
Most existing 3D CNNs for video representation learning are clip-based methods, and thus do not consider video-level temporal evolution of spatio-temporal features.
Knowledge Integration Networks for Action Recognition
We design a three-branch architecture consisting of a main branch for action recognition, and two auxiliary branches for human parsing and scene recognition which allow the model to encode the knowledge of human and scene for action recognition.
Cross-Batch Memory for Embedding Learning
This suggests that the features of instances computed at preceding iterations can be used to considerably approximate their features extracted by the current model.
Ranked #2 on
Image Retrieval
on In-Shop
Convolutional Character Networks
We evaluate CharNet on three standard benchmarks, where it consistently outperforms the state-of-the-art approaches [25, 24] by a large margin, e. g., with improvements of 65. 33%->71. 08% (with generic lexicon) on ICDAR 2015, and 54. 0%->69. 23% on Total-Text, on end-to-end text recognition.
Ranked #2 on
Scene Text Detection
on ICDAR 2015
Label-PEnet: Sequential Label Propagation and Enhancement Networks for Weakly Supervised Instance Segmentation
Weakly-supervised instance segmentation aims to detect and segment object instances precisely, given imagelevel labels only.
Ranked #11 on
Image-level Supervised Instance Segmentation
on PASCAL VOC 2012 val
(using extra training data)
General Classification
Image-level Supervised Instance Segmentation
+7
Dual-Stream Pyramid Registration Network
We propose a Dual-Stream Pyramid Registration Network (referred as Dual-PRNet) for unsupervised 3D medical image registration.
The iMaterialist Fashion Attribute Dataset
The dataset is constructed from over one million fashion images with a label space that includes 8 groups of 228 fine-grained attributes in total.
Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning
A family of loss functions built on pair-based computation have been proposed in the literature which provide a myriad of solutions for deep metric learning.
Ranked #4 on
Image Retrieval
on In-Shop
Compatible and Diverse Fashion Image Inpainting
The latent representations are jointly optimized with the corresponding generation network to condition the synthesis process, encouraging a diverse set of generated results that are visually compatible with existing fashion garments.
Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge
This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i. e., 2012-2018.
Deep Metric Learning with Hierarchical Triplet Loss
(i) we construct a hierarchical class-level tree where neighboring classes are merged recursively.
Ranked #8 on
Image Retrieval
on CARS196
CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images
We present a simple yet efficient approach capable of training deep neural networks on large-scale weakly-supervised web images, which are crawled raw from the Internet by using text queries, without any human annotation.
Ranked #1 on
Image Classification
on Clothing1M (using clean data)
(using extra training data)
An end-to-end TextSpotter with Explicit Alignment and Attention
This allows the two tasks to work collaboratively by shar- ing convolutional features, which is critical to identify challenging text instances.
Single Shot Text Detector with Regional Attention
Our text detector achieves an F-measure of 77% on the ICDAR 2015 bench- mark, advancing the state-of-the-art results in [18, 28].
Ranked #4 on
Scene Text Detection
on COCO-Text
Temporal HeartNet: Towards Human-Level Automatic Analysis of Fetal Cardiac Screening Video
We present an automatic method to describe clinically useful information about scanning, and to guide image interpretation in ultrasound (US) videos of the fetal heart.
Knowledge Guided Disambiguation for Large-Scale Scene Classification with Multi-Resolution CNNs
Convolutional Neural Networks (CNNs) have made remarkable progress on scene recognition, partially due to these recent large-scale scene datasets, such as the Places and Places2.
Detecting Text in Natural Image with Connectionist Text Proposal Network
We propose a novel Connectionist Text Proposal Network (CTPN) that accurately localizes text lines in natural image.
Accurate Text Localization in Natural Image with Cascaded Convolutional Text Network
We propose a novel Cascaded Convolutional Text Network (CCTN) that joints two customized convolutional networks for coarse-to-fine text localization.
Text-attentional convolutional neural network for scene text detection
Recent deep learning models have demonstrated strong capabilities for classifying text and non-text components in natural images.
Locally-Supervised Deep Hybrid Model for Scene Recognition
Secondly, we propose a new Local Convolutional Supervision (LCS) layer to enhance the local structure of the image by directly propagating the label information to the convolutional layers.
Text-Attentional Convolutional Neural Networks for Scene Text Detection
The rich supervision information enables the Text-CNN with a strong capability for discriminating ambiguous texts, and also increases its robustness against complicated background components.
Local Multi-Grouped Binary Descriptor with Ring-based Pooling Configuration and Optimization
The performance of RMGD was evaluated on a number of publicly available benchmarks, where the RMGD outperforms the state-of-the-art binary descriptors significantly.
Places205-VGGNet Models for Scene Recognition
We verify the performance of trained Places205-VGGNet models on three datasets: MIT67, SUN397, and Places205.
Local Color Contrastive Descriptor for Image Classification
Our descriptor enriches local image representation with both color and contrast information.
Reading Scene Text in Deep Convolutional Sequences
We develop a Deep-Text Recurrent Network (DTRN) that regards scene text reading as a sequence labelling problem.
Robust Face Recognition with Structural Binary Gradient Patterns
To discover underlying local structures in the gradient domain, we compute image gradients from multiple directions and simplify them into a set of binary strings.
