Search Results for author:
Found 79 papers, 29 papers with code
Adaptive Variance Based Label Distribution Learning For Facial Age Estimation
Some existing methods adopt distribution learning to tackle this issue by exploiting the semantic correlation between age labels.
Ranked #6 on
Age Estimation
on MORPH album2 (Caucasian)
Large Batch Optimization for Object Detection: Training COCO in 12 Minutes
Most of existing object detectors usually adopt a small training batch size ( ~16), which severely hinders the whole community from exploring large-scale datasets due to the extremely long training procedure.
Blended Grammar Network for Human Parsing
Although human parsing has made great progress, it still faces a challenge, i. e., how to extract the whole foreground from similar or cluttered scenes effectively.
Occlusion-Aware Siamese Network for Human Pose Estimation
To overcome the defects caused by the erasing operation, we perform feature reconstruction to recover the information destroyed by occlusion and details lost in cleaning procedure.
MathPhys-Guided Coarse-to-Fine Anomaly Synthesis with SQE-Driven Bi-Level Optimization for Anomaly Detection
Anomaly detection is a crucial task in computer vision, yet collecting real-world defect images is inherently difficult due to the rarity and unpredictability of anomalies.
An Empirical Study of Validating Synthetic Data for Text-Based Person Retrieval
(1) We propose an inter-class image generation pipeline, in which an automatic prompt construction strategy is introduced to guide generative Artificial Intelligence (AI) models in generating various inter-class images without reliance on original data.
Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learning
Large Vision-Language Models (LVLMs) typically follow a two-stage training paradigm-pretraining and supervised fine-tuning.
PhysVLM: Enabling Visual Language Models to Understand Robotic Physical Reachability
Specifically, the S-P Map abstracts a robot's physical reachability into a generalized spatial representation, independent of specific robot configurations, allowing the model to focus on reachability features rather than robot-specific parameters.
Synthetic Data is an Elegant GIFT for Continual Vision-Language Models
Pre-trained Vision-Language Models (VLMs) require Continual Learning (CL) to efficiently update their knowledge and adapt to various downstream tasks without retraining from scratch.
FLARE: A Framework for Stellar Flare Forecasting using Stellar Physical Properties and Historical Records
Stellar flare events are critical observational samples for astronomical research; however, recorded flare events remain limited.
A Benchmark for Crime Surveillance Video Analysis with Large Models
To fill this gap, we propose a benchmark for crime surveillance video analysis with large models denoted as UCVL, including 1, 829 videos and reorganized annotations from the UCF-Crime and UCF-Crime Annotation datasets.
Systematic Outliers in Large Language Models
Outliers have been widely observed in Large Language Models (LLMs), significantly impacting model performance and posing challenges for model compression.
MME-Industry: A Cross-Industry Multimodal Evaluation Benchmark
With the rapid advancement of Multimodal Large Language Models (MLLMs), numerous evaluation benchmarks have emerged.
FiLo++: Zero-/Few-Shot Anomaly Detection by Fused Fine-Grained Descriptions and Deformable Localization
However, their handcrafted generic descriptions fail to capture the diverse range of anomalies that may emerge in different objects, and simple patch-level image-text matching often struggles to localize anomalous regions of varying shapes and sizes.
LINK: Adaptive Modality Interaction for Audio-Visual Video Parsing
Audio-visual video parsing focuses on classifying videos through weak labels while identifying events as either visible, audible, or both, alongside their respective temporal boundaries.
Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence
Large vision-language models (LVLMs) have made substantial progress in integrating large language models (LLMs) with visual inputs, enabling advanced multimodal reasoning.
UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection
Visual Anomaly Detection (VAD) aims to identify abnormal samples in images that deviate from normal patterns, covering multiple domains, including industrial, logical, and medical fields.
Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection
Overfitting has long been stigmatized as detrimental to model performance, especially in the context of anomaly detection.
Monocular Lane Detection Based on Deep Learning: A Survey
Lane detection plays an important role in autonomous driving perception systems.
SEEKR: Selective Attention-Guided Knowledge Retention for Continual Learning of Large Language Models
In this work, we first explore and emphasize the importance of attention weights in knowledge retention, and then propose a SElective attEntion-guided Knowledge Retention method (SEEKR) for data-efficient replay-based continual learning of large language models (LLMs).
Griffon-G: Bridging Vision-Language and Vision-Centric Tasks via Large Multimodal Models
None of the LMMs have yet comprehensively unified both types of tasks within a single model, as seen in Large Language Models in the natural language processing field.
Enhancing Text-to-SQL Capabilities of Large Language Models via Domain Database Knowledge Injection
However, LLMs face challenges due to hallucination issues and a lack of domain-specific database knowledge(such as table schema and cell values).
The BRAVO Semantic Segmentation Challenge Results in UNCV2024
We propose the unified BRAVO challenge to benchmark the reliability of semantic segmentation models under realistic perturbations and unknown out-of-distribution (OOD) scenarios.
MROVSeg: Breaking the Resolution Curse of Vision-Language Models in Open-Vocabulary Image Segmentation
Pretrained vision-language models (VLMs), \eg CLIP, are increasingly used to bridge the gap between open- and close-vocabulary recognition in open-vocabulary image segmentation.
AnyDesign: Versatile Area Fashion Editing via Mask-Free Diffusion
Moreover, these methods are limited in the variety of clothing types they can handle, as most datasets focus on people in clean backgrounds and only include generic garments such as tops, pants, and dresses.
Auto DragGAN: Editing the Generative Image Manifold in an Autoregressive Manner
Specifically, we develop a transformer encoder-decoder based network named 'Latent Predictor' to predict the latent code motion trajectories from handle points to target points in an autoregressive manner.
Recurrent Context Compression: Efficiently Expanding the Context Window of LLM
To extend the context length of Transformer-based large language models (LLMs) and improve comprehension capabilities, we often face limitations due to computational resources and bounded memory storage capacity.
VS-Assistant: Versatile Surgery Assistant on the Demand of Surgeons
In this work, by leveraging advanced multimodal large language models (MLLMs), we propose a Versatile Surgery Assistant (VS-Assistant) that can accurately understand the surgeon's intention and complete a series of surgical understanding tasks, e. g., surgical scene analysis, surgical instrument detection, and segmentation on demand.
Pattern-Aware Chain-of-Thought Prompting in Large Language Models
In this paper, we propose Pattern-Aware CoT, a prompting method that considers the diversity of demonstration patterns.
PM-VIS: High-Performance Box-Supervised Video Instance Segmentation
Our PM-VIS model, trained with high-quality pseudo mask annotations, demonstrates strong ability in instance mask prediction, achieving state-of-the-art performance on the YouTube-VIS 2019, YouTube-VIS 2021, and OVIS validation sets, notably narrowing the gap between box-supervised and fully supervised VIS methods.
FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization
Zero-shot anomaly detection (ZSAD) methods entail detecting anomalies directly without access to any known normal or abnormal samples within the target item categories.
Ranked #4 on
zero-shot anomaly detection
on MVTec AD
Optimization of Prompt Learning via Multi-Knowledge Representation for Vision-Language Models
This limitation restricts the capabilities of pretrained VLMs and can result in incorrect predictions in downstream tasks.
Griffon v2: Advancing Multimodal Perception with High-Resolution Scaling and Visual-Language Co-Referring
Large Vision Language Models have achieved fine-grained object perception, but the limitation of image resolution remains a significant obstacle to surpass the performance of task-specific experts in complex and dense scenarios.
BFRFormer: Transformer-based generator for Real-World Blind Face Restoration
Blind face restoration is a challenging task due to the unknown and complex degradation.
PFDM: Parser-Free Virtual Try-on via Diffusion Model
Virtual try-on can significantly improve the garment shopping experiences in both online and in-store scenarios, attracting broad interest in computer vision.
Self-Supervised Representation Learning from Arbitrary Scenarios
To address this conflict this work abandons the non-generalizable global-level constraints and proposes explicit patch-level contrastive learning as a solution.
Fluctuation-based Adaptive Structured Pruning for Large Language Models
Retraining-free is important for LLMs' pruning methods.
Mitigating Hallucination in Visual Language Models with Visual Supervision
Large vision-language models (LVLMs) suffer from hallucination a lot, generating responses that apparently contradict to the image content occasionally.
Continual Instruction Tuning for Large Multimodal Models
2) Are the existing three classes of continual learning methods still applicable to the continual instruction tuning of LMMs?
Griffon: Spelling out All Object Locations at Any Granularity with Large Language Models
Current LVLMs are predominantly constrained to locate a single, pre-existing object.
Surgical Temporal Action-aware Network with Sequence Regularization for Phase Recognition
Specifically, we propose an efficient multi-scale surgical temporal action (MS-STA) module, which integrates visual features with spatial and temporal knowledge of surgical actions at the cost of 2D networks.
ChineseWebText: Large-scale High-quality Chinese Web Text Extracted with Effective Evaluation Model
Using our proposed approach, we release the largest and latest large-scale high-quality Chinese web text ChineseWebText, which consists of 1. 42 TB and each text is associated with a quality score, facilitating the LLM researchers to choose the data according to the desired quality thresholds.
SSPFusion: A Semantic Structure-Preserving Approach for Infrared and Visible Image Fusion
Most existing learning-based infrared and visible image fusion (IVIF) methods exhibit massive redundant information in the fusion images, i. e., yielding edge-blurring effect or unrecognizable for object detectors.
AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models
Large Vision-Language Models (LVLMs) such as MiniGPT-4 and LLaVA have demonstrated the capability of understanding images and achieved remarkable performance in various visual tasks.
Fast Segment Anything
In this paper, we propose a speed-up alternative method for this fundamental task with comparable performance.
Ranked #4 on
Zero-Shot Instance Segmentation
on LVIS v1.0 val
FreConv: Frequency Branch-and-Integration Convolutional Networks
In the high-frequency branch, a derivative-filter-like architecture is designed to extract the high-frequency information while a light extractor is employed in the low-frequency branch because the low-frequency information is usually redundant.
ZBS: Zero-shot Background Subtraction via Instance-level Background Modeling and Foreground Selection
However, previous unsupervised deep learning BGS algorithms perform poorly in sophisticated scenarios such as shadows or night lights, and they cannot detect objects outside the pre-defined categories.
Efficient Masked Autoencoders with Self-Consistency
Besides, we design the self-consistency learning to further maintain the consistency of predictions of overlapping masked patches among parts.
Temporal-Channel Topology Enhanced Network for Skeleton-Based Action Recognition
Most current methods adopt graph convolutional network (GCN) for topology modeling, but GCN-based methods are limited in long-distance correlation modeling and generalizability.
Masked Contrastive Pre-Training for Efficient Video-Text Retrieval
Our MAC aims to reduce video representation's spatial and temporal redundancy in the VidLP model by a mask sampling mechanism to improve pre-training efficiency.
Ranked #40 on
Video Retrieval
on MSR-VTT-1kA
(using extra training data)
Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks
Obj2Seq is able to flexibly determine input categories to satisfy customized requirements, and be easily extended to different visual tasks.
Transfering Low-Frequency Features for Domain Adaptation
Previous unsupervised domain adaptation methods did not handle the cross-domain problem from the perspective of frequency for computer vision.
Plug-and-Play Pseudo Label Correction Network for Unsupervised Person Re-identification
Clustering-based methods, which alternate between the generation of pseudo labels and the optimization of the feature extraction network, play a dominant role in both unsupervised learning (USL) and unsupervised domain adaptive (UDA) person re-identification (Re-ID).
UniVIP: A Unified Framework for Self-Supervised Visual Pre-training
Furthermore, our method can also exploit single-centric-object dataset such as ImageNet and outperforms BYOL by 2. 5% with the same pre-training epochs in linear probing, and surpass current self-supervised object detection methods on COCO dataset, demonstrating its universality and potential.
PASS: Part-Aware Self-Supervised Pre-Training for Person Re-Identification
PASS learns to match the output of the local views and global views on the same [PART].
Pruning-aware Sparse Regularization for Network Pruning
MaskSparsity imposes the fine-grained sparse regularization on the specific filters selected by a pruning mask, rather than all the filters of the model.
C2AM Loss: Chasing a Better Decision Boundary for Long-Tail Object Detection
The decision boundary between any two categories is the angular bisector of their weight vectors.
Multi-initialization Optimization Network for Accurate 3D Human Pose and Shape Estimation
In the second stage, we design a mesh refinement transformer (MRT) to respectively refine each coarse reconstruction result via a self-attention mechanism.
Ranked #74 on
3D Human Pose Estimation
on 3DPW
(MPJPE metric)
DPT: Deformable Patch-based Transformer for Visual Recognition
To address this problem, we propose a new Deformable Patch (DePatch) module which learns to adaptively split the images into patches with different positions and scales in a data-driven way rather than using predefined fixed patches.
Ranked #17 on
Semantic Segmentation
on DensePASS
OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation
In this paper, we propose an Omni-perception Pre-Trainer (OPT) for cross-modal understanding and generation, by jointly modeling visual, text and audio resources.
Ranked #1 on
Image Retrieval
on Localized Narratives
Improving Multiple Object Tracking With Single Object Tracking
Despite considerable similarities between multiple object tracking (MOT) and single object tracking (SOT) tasks, modern MOT methods have not benefited from the development of SOT ones to achieve satisfactory performance.
MST: Masked Self-Supervised Transformer for Visual Representation
More importantly, the masked tokens together with the remaining tokens are further recovered by a global image decoder, which preserves the spatial information of the image and is more friendly to the downstream dense prediction tasks.
Adaptive Class Suppression Loss for Long-Tail Object Detection
To address the problem of long-tail distribution for the large vocabulary object detection task, existing methods usually divide the whole categories into several groups and treat each group with different strategies.
AAformer: Auto-Aligned Transformer for Person Re-Identification
In this article, we introduce an alignment scheme in transformer architecture for the first time and propose the auto-aligned transformer (AAformer) to automatically locate both the human parts and nonhuman ones at patch level.
High-Performance Discriminative Tracking With Transformers
End-to-end discriminative trackers improve the state of the art significantly, yet the improvement in robustness and efficiency is restricted by the conventional discriminative model, i. e., least-squares based regression.
Task Decoupled Knowledge Distillation For Lightweight Face Detectors
This method decouples the distillation task of face detection into two subtasks, i. e., the classification distillation subtask and the regression distillation subtask.
Identity-Guided Human Semantic Parsing for Person Re-Identification
In this paper, we propose the identity-guided human semantic parsing approach (ISP) to locate both the human body parts and personal belongings at pixel-level for aligned person re-ID only with person identity labels.
Ranked #21 on
Person Re-Identification
on Occluded-DukeMTMC
Learning Feature Embeddings for Discriminant Model based Tracking
After observing that the features used in most online discriminatively trained trackers are not optimal, in this paper, we propose a novel and effective architecture to learn optimal feature embeddings for online discriminative tracking.
Semantic Alignment: Finding Semantically Consistent Ground-truth for Facial Landmark Detection
Despite this, we notice that the semantic ambiguity greatly degrades the detection performance.
Ranked #1 on
Face Alignment
on 300W
(NME_inter-pupil (%, Full) metric)
Recurrent Calibration Network for Irregular Text Recognition
In this paper, we propose a novel Recurrent Calibration Network (RCN) for irregular scene text recognition.
High-speed Tracking with Multi-kernel Correlation Filters
In this paper, we will introduce the MKL into KCF in a different way than MKCF.
Ranked #34 on
Video Object Tracking
on NT-VOT211
Fast Kernelized Correlation Filters without Boundary Effect
To achieve the fast training and detection, a set of cyclic bases is introduced to construct the filter.
On the Relations of Correlation Filter Based Trackers and Struck
In recent years, two types of trackers, namely correlation filter based tracker (CF tracker) and structured output tracker (Struck), have exhibited the state-of-the-art performance.
Reading Scene Text with Attention Convolutional Sequence Modeling
Reading text in the wild is a challenging task in the field of computer vision.
CoupleNet: Coupling Global Structure with Local Parts for Object Detection
To fully explore the local and global properties, in this paper, we propose a novel fully convolutional network, named as CoupleNet, to couple the global structure with local parts for object detection.
Ranked #5 on
Object Detection
on PASCAL VOC 2007
Fast Deep Matting for Portrait Animation on Mobile Phone
Finally, an automatic portrait animation system based on fast deep matting is built on mobile devices, which does not need any interaction and can realize real-time matting with 15 fps.
Joint Background Reconstruction and Foreground Segmentation via A Two-stage Convolutional Neural Network
In the first stage, a convolutional encoder-decoder sub-network is employed to reconstruct the background images and encode rich prior knowledge of background scenes.
Learning Adaptive Receptive Fields for Deep Image Parsing Network
In this paper, we introduce a novel approach to regulate receptive field in deep image parsing network automatically.
Relaxing From Vocabulary: Robust Weakly-Supervised Deep Learning for Vocabulary-Free Image Tagging
The development of deep learning has empowered machines with comparable capability of recognizing limited image categories to human beings.
