Search Results for author:
Found 88 papers, 53 papers with code
MP-Mat: A 3D-and-Instance-Aware Human Matting and Editing Framework with Multiplane Representation
In this work, we address this by introducing MP-Mat, a novel 3D-and-instance-aware matting framework with multiplane representation, where the multiplane concept is designed from two different perspectives: scene geometry level and instance level.
DMPT: Decoupled Modality-aware Prompt Tuning for Multi-modal Object Re-identification
Current multi-modal object re-identification approaches based on large-scale pre-trained backbones (i. e., ViT) have displayed remarkable progress and achieved excellent performance.
Taming Consistency Distillation for Accelerated Human Image Animation
Recent advancements in human image animation have been propelled by video diffusion models, yet their reliance on numerous iterative denoising steps results in high inference costs and slow speeds.
UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion Transformer
Furthermore, we adopt a simple concatenation operation to integrate the reference appearance into the model and incorporate the pose information of the reference image for enhanced pose alignment.
NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results
Cross-Domain Few-Shot Object Detection (CD-FSOD) poses significant challenges to existing object detection and few-shot detection models when applied across domains.
Cross-Domain Few-Shot
Cross-Domain Few-Shot Object Detection
+3
Exploring the Evolution of Physics Cognition in Video Generation: A Survey
Recent advancements in video generation have witnessed significant progress, especially with the rapid advancement of diffusion models.
FedPCA: Noise-Robust Fair Federated Learning via Performance-Capacity Analysis
In this paper, we attribute this competition to the homogeneity in loss patterns exhibited by rare and mislabeled data clients, preventing existing loss-based fair and robust FL methods from effectively distinguishing and handling these two distinct client types.
Object-Aware Video Matting with Cross-Frame Guidance
Recently, trimap-free methods have drawn increasing attention in human video matting due to their promising performance.
CTR-Driven Advertising Image Generation with Multimodal Large Language Models
In web data, advertising images are crucial for capturing user attention and improving advertising effectiveness.
Adaptive Prototype Replay for Class Incremental Semantic Segmentation
However, they overlook a critical issue: in CISS, the representation of class knowledge is updated continuously through incremental learning, whereas prototype replay methods maintain fixed prototypes.
Class-Incremental Semantic Segmentation
Incremental Learning
Structural Pruning via Spatial-aware Information Redundancy for Semantic Segmentation
Within this framework, we introduce a spatial-aware redundancy metric based on feature maps, thus endowing the pruning process with location sensitivity to better adapt to pruning segmentation networks.
Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity
For efficient anomaly detection in long videos, we propose the Anomaly-focused Temporal Sampler (ATS).
Improving Multi-modal Large Language Model through Boosting Vision Capabilities
QLadder employs a learnable ``\textit{ladder}'' structure to deeply aggregates the intermediate representations from the frozen pretrained visual encoder (e. g., CLIP image encoder).
Ranked #165 on
Visual Question Answering
on MM-Vet
DFIMat: Decoupled Flexible Interactive Matting in Multi-Person Scenarios
(2) Existing works are limited to a single type of user input, which is ineffective for intention understanding and also inefficient for user operation.
Replace Anyone in Videos
Recent advancements in controllable human-centric video generation, particularly with the rise of diffusion models, have demonstrated considerable progress.
Cross-video Identity Correlating for Person Re-identification Pre-training
For example, compared with the previous state-of-the-art~\cite{ISR}, CION with the same ResNet50-IBN achieves higher mAP of 93. 3\% and 74. 3\% on Market1501 and MSMT17, while only utilizing 8\% training samples.
Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM
We train a lightweight temporal sampler to select frames with high anomaly response and fine-tune a multimodal large language model (LLM) to generate explanatory content.
Open-Vocabulary Semantic Segmentation with Image Embedding Balancing
To learn a consistent semantic structure from CLIP, the SSC Loss aligns the inter-classes affinity in the image feature space with that in the text feature space of CLIP, thereby improving the generalization ability of our model.
UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation
First, to reduce the optimization difficulty and ensure temporal coherence, we map the reference image along with the posture guidance and noise video into a common feature space by incorporating a unified video diffusion model.
Tunnel Try-on: Excavating Spatial-temporal Tunnels for High-quality Virtual Try-on in Videos
To generate coherent motions, we first leverage the Kalman filter to construct smooth crops in the focus tunnel and inject the position embedding of the tunnel into attention layers to improve the continuity of the generated videos.
REPAIR: Rank Correlation and Noisy Pair Half-replacing with Memory for Noisy Correspondence
Unfortunately, obtaining precise annotations in the multimodal field is expensive, which has prompted some methods to tackle the mismatched data pair issue in cross-modal matching contexts, termed as noisy correspondence.
GlanceVAD: Exploring Glance Supervision for Label-efficient Video Anomaly Detection
In recent years, video anomaly detection has been extensively investigated in both unsupervised and weakly supervised settings to alleviate costly temporal labeling.
Spatial Cascaded Clustering and Weighted Memory for Unsupervised Person Re-identification
We introduce the Spatial Cascaded Clustering and Weighted Memory (SCWM) method to address these challenges.
Real-Time Exposure Correction via Collaborative Transformations and Adaptive Sampling
Specifically the global transformation adjusts the overall appearance using image-adaptive 3D LUTs to provide decent global contrast and sharp details while the pixel transformation compensates for local context.
SCTNet: Single-Branch CNN with Transformer Semantic Information for Real-Time Segmentation
Recent real-time semantic segmentation methods usually adopt an additional semantic branch to pursue rich long-range context.
A Recipe for Scaling up Text-to-Video Generation with Text-free Videos
Following such a pipeline, we study the effect of doubling the scale of training set (i. e., video-only WebVid10M) with some randomly collected text-free videos and are encouraged to observe the performance improvement (FID from 9. 67 to 8. 19 and FVD from 484 to 441), demonstrating the scalability of our approach.
Ranked #7 on
Text-to-Video Generation
on MSR-VTT
VideoLCM: Video Latent Consistency Model
Consistency models have demonstrated powerful capability in efficient image generation and allowed synthesis within a few sampling steps, alleviating the high computational cost in diffusion models.
Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation
At the structure level, we decompose the T2V task into two steps, including spatial reasoning and temporal reasoning, using a unified denoiser.
Ranked #6 on
Text-to-Video Generation
on MSR-VTT
UFineBench: Towards Text-based Person Retrieval with Ultra-fine Granularity
Firstly, we construct a new \textbf{dataset} named UFine6926.
Lookup Table meets Local Laplacian Filter: Pyramid Reconstruction Network for Tone Mapping
Furthermore, we utilize local Laplacian filters to refine the edge details in the high-frequency components in an adaptive manner.
Few-shot Action Recognition with Captioning Foundation Models
In this paper, we develop an effective plug-and-play framework called CapFSAR to exploit the knowledge of multimodal models without manually annotating text.
Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning
When pre-training on the large-scale Kinetics-710, we achieve 89. 7% on Kinetics-400 with a frozen ViT-L model, which verifies the scalability of DiST.
HR-Pro: Point-supervised Temporal Action Localization via Hierarchical Reliability Propagation
For snippet-level learning, we introduce an online-updated memory to store reliable snippet prototypes for each class.
Ranked #1 on
Weakly Supervised Action Localization
on BEOID
Towards General Low-Light Raw Noise Synthesis and Modeling
To address this issue, we introduce a new perspective to synthesize the signal-independent noise by a generative model.
Ranked #2 on
Image Denoising
on SID SonyA7S2 x300
Conditional Boundary Loss for Semantic Segmentation
We conduct extensive experiments on ADE20K, Cityscapes, and Pascal Context, and the results show that applying the CBL to various popular segmentation networks can significantly improve the mIoU and boundary F-score performance.
Ranked #25 on
Semantic Segmentation
on Cityscapes val
PLIP: Language-Image Pre-training for Person Representation Learning
To address this issue, we propose a novel language-image pre-training framework for person representation learning, termed PLIP.
Ranked #7 on
Text based Person Retrieval
on ICFG-PEDES
MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognition
To address these issues, we develop a Motion-augmented Long-short Contrastive Learning (MoLo) method that contains two crucial components, including a long-short contrastive objective and a motion autodecoder.
CLIP-guided Prototype Modulating for Few-shot Action Recognition
Learning from large-scale contrastive language-image pre-training like CLIP has shown remarkable success in a wide range of downstream tasks recently, but it is still under-explored on the challenging few-shot action recognition (FSAR) task.
Semantic Segmentation via Pixel-to-Center Similarity Calculation
Under this novel view, we propose a Class Center Similarity layer (CCS layer) to address the above-mentioned challenges by generating adaptive class centers conditioned on different scenes and supervising the similarities between class centers.
HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognition
To be specific, HyRSM++ consists of two key components, a hybrid relation module and a temporal set matching metric.
Parallel Reasoning Network for Human-Object Interaction Detection
Human-Object Interaction (HOI) detection aims to learn how human interacts with surrounding objects.
DMRNet++: Learning Discriminative Features with Decoupled Networks and Enriched Pairs for One-Step Person Search
Person search aims at localizing and recognizing query persons from raw video frames, which is a combination of two sub-tasks, i. e., pedestrian detection and person re-identification.
Ranked #3 on
Person Search
on PRW
Learning a Condensed Frame for Memory-Efficient Video Class-Incremental Learning
The former is to reduce the memory cost by preserving only one condensed frame instead of the whole video, while the latter aims to compensate the lost spatio-temporal details in the Frame Condensing stage.
MAR: Masked Autoencoders for Efficient Action Recognition
Inspired by this, we propose propose Masked Action Recognition (MAR), which reduces the redundant computation by discarding a proportion of patches and operating only on a part of the videos.
Ranked #11 on
Action Recognition
on Something-Something V2
Context-aware Proposal Network for Temporal Action Detection
This technical report presents our first place winning solution for temporal action detection task in CVPR-2022 AcitivityNet Challenge.
Hybrid Relation Guided Set Matching for Few-shot Action Recognition
To overcome the two limitations, we propose a novel Hybrid Relation guided Set Matching (HyRSM) approach that incorporates two key components: hybrid relation module and set matching metric.
Learning from Untrimmed Videos: Self-Supervised Video Representation Learning with Hierarchical Consistency
In this work, we aim to learn representations by leveraging more abundant information in untrimmed videos.
Joint CNN and Transformer Network via weakly supervised Learning for efficient crowd counting
However, the transformer directly partitions the crowd images into a series of tokens, which may not be a good choice due to each pedestrian being an independent individual, and the parameter number of the network is very large.
Multi-Centroid Representation Network for Domain Adaptive Person Re-ID
First, we present a Domain-Specific Contrastive Learning (DSCL) mechanism to fully explore intradomain information by comparing samples only from the same domain.
Contrastive Learning
Domain Adaptive Person Re-Identification
+2
Modality-Aware Triplet Hard Mining for Zero-shot Sketch-Based Image Retrieval
By combining two fundamental learning approaches in DML, e. g., classification training and pairwise training, we set up a strong baseline for ZS-SBIR.
Implicit Neural Deformation for Sparse-View Face Reconstruction
In this work, we present a new method for 3D face reconstruction from sparse-view RGB images.
Unsupervised Low-Light Image Enhancement via Histogram Equalization Prior
We introduce a Noise Disentanglement Module (NDM) to disentangle the noise and content in the reflectance maps with the reliable aid of unpaired clean images.
Ranked #3 on
Low-Light Image Enhancement
on MEF
Attribute-specific Control Units in StyleGAN for Fine-grained Image Manipulation
Image manipulation with StyleGAN has been an increasing concern in recent years. Recent works have achieved tremendous success in analyzing several semantic latent spaces to edit the attributes of the generated images. However, due to the limited semantic and spatial manipulation precision in these latent spaces, the existing endeavors are defeated in fine-grained StyleGAN image manipulation, i. e., local attribute translation. To address this issue, we discover attribute-specific control units, which consist of multiple channels of feature maps and modulation styles.
CondNet: Conditional Classifier for Scene Segmentation
The last layer of FCN is typically a global classifier (1x1 convolution) to recognize each pixel to a semantic label.
Ranked #21 on
Semantic Segmentation
on PASCAL Context
Weakly Supervised Person Search with Region Siamese Networks
Large-scale labeled training data is often difficult to collect, especially for person identities.
ParamCrop: Parametric Cubic Cropping for Video Contrastive Learning
The visualizations show that ParamCrop adaptively controls the center distance and the IoU between two augmented views, and the learned change in the disparity along the training process is beneficial to learning a strong representation.
Exploring Stronger Feature for Temporal Action Localization
Temporal action localization aims to localize starting and ending time with action category.
OadTR: Online Action Detection with Transformers
Most recent approaches for online action detection tend to apply Recurrent Neural Network (RNN) to capture long-range temporal structure.
Ranked #8 on
Online Action Detection
on THUMOS'14
Weakly-Supervised Temporal Action Localization Through Local-Global Background Modeling
Then our proposed Local-Global Background Modeling Network (LGBM-Net) is trained to localize instances by using only video-level labels based on Multi-Instance Learning (MIL).
Weakly-supervised Learning
Weakly-supervised Temporal Action Localization
+1
Proposal Relation Network for Temporal Action Detection
We calculate the detection results by assigning the proposals with corresponding classification results.
Ranked #3 on
Temporal Action Localization
on ActivityNet-1.3
(using extra training data)
A Stronger Baseline for Ego-Centric Action Detection
This technical report analyzes an egocentric video action detection method we used in the 2021 EPIC-KITCHENS-100 competition hosted in CVPR2021 Workshop.
Towards Training Stronger Video Vision Transformers for EPIC-KITCHENS-100 Action Recognition
In this paper, we present empirical results for training a stronger video vision transformer on the EPIC-KITCHENS-100 Action Recognition dataset.
Hybrid attention network based on progressive embedding scale-context for crowd counting
In this paper, we propose a Hybrid Attention Network (HAN) by employing Progressive Embedding Scale-context (PES) information, which enables the network to simultaneously suppress noise and adapt head scale variation.
Lite-HRNet: A Lightweight High-Resolution Network
We introduce a lightweight unit, conditional channel weighting, to replace costly pointwise (1x1) convolutions in shuffle blocks.
Ranked #33 on
Pose Estimation
on COCO test-dev
(using extra training data)
Self-Supervised Learning for Semi-Supervised Temporal Action Proposal
In this paper, we focus on applying the power of self-supervised methods to improve semi-supervised action proposal generation.
Ranked #2 on
Semi-Supervised Action Detection
on ActivityNet-1.3
Temporal Context Aggregation Network for Temporal Action Proposal Refinement
In this paper, we propose Temporal Context Aggregation Network (TCANet) to generate high-quality action proposals through "local and global" temporal context aggregation and complementary as well as progressive boundary refinement.
Ranked #10 on
Temporal Action Localization
on ActivityNet-1.3
Decoupled and Memory-Reinforced Networks: Towards Effective Feature Learning for One-Step Person Search
Specifically, to reconcile the conflicts of multiple objectives, we simplify the standard tightly coupled pipelines and establish a deeply decoupled multi-task learning framework.
Ranked #8 on
Person Search
on PRW
Weakly Supervised Text-Based Person Re-Identification
Specifically, to alleviate the intra-class variations, a clustering method is utilized to generate pseudo labels for both visual and textual instances.
Exploiting Learnable Joint Groups for Hand Pose Estimation
This is different from the previous methods where all the joints are considered holistically and share the same feature.
Do Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians
In the conventional person Re-ID setting, it is widely assumed that cropped person images are for each individual.
Representative Graph Neural Network
In this paper, we present a Representative Graph (RepGraph) layer to dynamically sample a few representative features, which dramatically reduces redundancy.
Multi-Level Temporal Pyramid Network for Action Detection
By this means, the proposed MLTPN can learn rich and discriminative features for different action instances with different durations.
Adversarial Semantic Data Augmentation for Human Pose Estimation
Human pose estimation is the task of localizing body keypoints from still images.
CBR-Net: Cascade Boundary Refinement Network for Action Detection: Submission to ActivityNet Challenge 2020 (Task 1)
In this report, we present our solution for the task of temporal action localization (detection) (task 1) in ActivityNet Challenge 2020.
Temporal Fusion Network for Temporal Action Localization:Submission to ActivityNet Challenge 2020 (Task E)
This technical report analyzes a temporal action localization method we used in the HACS competition which is hosted in Activitynet Challenge 2020. The goal of our task is to locate the start time and end time of the action in the untrimmed video, and predict action category. Firstly, we utilize the video-level feature information to train multiple video-level action classification models.
Relevant Region Prediction for Crowd Counting
The module builds a fully connected directed graph between the regions of different density where each node (region) is represented by weighted global pooled feature, and GCN is learned to map this region graph to a set of relation-aware regions representations.
Domain Adaptation for Image Dehazing
By training image translation and dehazing network in an end-to-end manner, we can obtain better effects of both image translation and dehazing.
Ranked #5 on
Image Dehazing
on RESIDE-6K
BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation
We propose to treat these spatial details and categorical semantics separately to achieve high accuracy and high efficiency for realtime semantic segmentation.
Ranked #1 on
Real-Time Semantic Segmentation
on COCO-Stuff
Context Prior for Scene Segmentation
Given an input image and corresponding ground truth, Affinity Loss constructs an ideal affinity map to supervise the learning of Context Prior.
Ranked #1 on
Scene Understanding
on ADE20K val
GTNet: Generative Transfer Network for Zero-Shot Object Detection
FFU and BFU add the IoU variance to the results of CFU, yielding class-specific foreground and background features, respectively.
Re-ID Driven Localization Refinement for Person Search
The state-of-the-art methods train the detector individually, and the detected bounding boxes may be sub-optimal for the following re-ID task.
BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
Semantic segmentation requires both rich spatial information and sizeable receptive field.
Ranked #4 on
Semantic Segmentation
on SkyScapes-Dense
Dichotomous Image Segmentation
Real-Time Semantic Segmentation
+2
Learning a Discriminative Feature Network for Semantic Segmentation
Most existing methods of semantic segmentation still suffer from two aspects of challenges: intra-class inconsistency and inter-class indistinction.
Ranked #5 on
Semantic Segmentation
on PASCAL VOC 2012 test
Learning a Discriminative Prior for Blind Image Deblurring
We present an effective blind image deblurring method based on a data-driven discriminative prior. Our work is motivated by the fact that a good image prior should favor clear images over blurred images. In this work, we formulate the image prior as a binary classifier which can be achieved by a deep convolutional neural network (CNN). The learned prior is able to distinguish whether an input image is clear or not. Embedded into the maximum a posterior (MAP) framework, it helps blind deblurring in various scenarios, including natural, face, text, and low-illumination images. However, it is difficult to optimize the deblurring method with the learned image prior as it involves a non-linear CNN. Therefore, we develop an efficient numerical approach based on the half-quadratic splitting method and gradient decent algorithm to solve the proposed model. Furthermore, the proposed model can be easily extended to non-uniform deblurring. Both qualitative and quantitative experimental results show that our method performs favorably against state-of-the-art algorithms as well as domain-specific image deblurring approaches.
Multiple Target Tracking by Learning Feature Representation and Distance Metric Jointly
Designing a robust affinity model is the key issue in multiple target tracking (MTT).
Learning Scene-specific Object Detectors Based on a Generative-Discriminative Model with Minimal Supervision
In this paper, the proposed framework takes a remarkably different direction to resolve the multi-scene detection problem in a bottom-up fashion.
Scene Text Detection via Holistic, Multi-Channel Prediction
Recently, scene text detection has become an active research topic in computer vision and document analysis, because of its great importance and significant challenge.
Ranked #6 on
Scene Text Detection
on COCO-Text
Exemplar-based Linear Discriminant Analysis for Robust Object Tracking
However, the task in tracking is to search for a specific object, rather than an object category as in detection.
