Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks150 from public data
- 436
- Vision-Language Transformer and Query Generation for Referring Segmentation398
Transformer and multi-head attention are introduced and a Query Generation Module is proposed, which produces multiple sets of queries with different attention weights that represent the diversified comprehensions of the language expression from different aspects.
- GRES: Generalized Referring Expression Segmentation358
A region-based GRES baseline ReLA is proposed that adaptively divides the image into regions with subinstance clues, and explicitly models the region-region and region-language dependencies and achieves new state-of-the-art performance on the both newly proposed GRES and classic RES tasks.
- Transformer-Based Visual Segmentation: A Survey342
This survey provides a thorough overview of transformer-based visual segmentation, summarizing recent advancements and presents a meta-architecture that unifies all recent transformer-based approaches.
- MOSE: A New Dataset for Video Object Segmentation in Complex Scenes307
The experiments show that current VOS algorithms cannot well perceive objects in complex scenes, and there are unresolved challenges under complex scenes and more efforts are desired to explore these challenges in the future.
- MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions305
The results show that current RVOS methods cannot effectively address motion expression-guided video segmentation, and a large-scale dataset called MeViS is proposed, which contains numerous motion expressions to indicate target objects in complex environments.
- Boundary-Aware Feature Propagation for Scene Segmentation292
A boundary-aware feature propagation (BFP) module to harvest and propagate the local features within their regions isolated by the learned boundaries in the UAG-structured image and achieves new state-of-the-art segmentation performance on three challenging semantic segmentation datasets, i.e., PASCAL-Context, CamVid, and Cityscapes.
- Towards Open Vocabulary Learning: A Survey285
This paper thoroughly reviews open vocabulary learning, summarizing and analyzing recent developments in the field, and juxtaposing open vocabulary learning with analogous concepts such as zero-shot learning, open-set recognition, and out-of-distribution detection.
- Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imaging225
A principled Degradation-Aware Unfolding Framework (DAUF) that estimates parameters from the compressed image and physical mask, and then uses these parameters to control each iteration, and customize a novel Half-Shuffle Transformer (HST) that simultaneously captures local contents and non-local dependencies.
- VLT: Vision-Language Transformer and Query Generation for Referring Segmentation196
A Query Generation Module, which dynamically produces multiple sets of input-specific queries to represent the diverse comprehensions of language expression, and a Query Balance Module to selectively fuse the corresponding responses of the set of queries to enhance the model's ability in dealing with diverse language expressions.
- MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesis194
The proposed MINE is a continuous depth generalization of the Multiplane Images (MPI) by introducing the NEural radiance fields (NeRF) to perform novel view synthesis and depth estimation via dense 3D reconstruction from a single image.
- Semantic Correlation Promoted Shape-Variant Context for Segmentation193
This work proposes a novel paired convolution to infer the semantic correlation of the pair and based on that to generate a shape mask, of which the receptive field is controlled by the shape mask that varies with the appearance of input.
- 157
- OMG-Seg: Is One Model Good Enough for all Segmentation?140
It is shown that OMG-Seg, a transformer-based encoder-decoder architecture with task-specific queries and outputs, can support over ten distinct segmentation tasks and yet significantly reduce computational and parameter overhead across various tasks and datasets.
- Recovering the Unbiased Scene Graphs from the Biased Ones139
This paper shows that, due to the missing labels, SGG can be viewed as a "Learning from Positive and Unlabeled data" (PU learning) problem, where the reporting bias can be removed by recovering the unbiased probabilities from the biased ones by utilizing label frequencies.
- Feature Boosting Network For 3D Pose Estimation135
A context consistency gate (CCG) is introduced in this paper, with which the convolutional feature maps are modulated according to their consistency with the context representations, to improve the reliability of the features for representing each body part and enhance the LSTD module.
- VGSG: Vision-Guided Semantic-Group Network for Text-Based Person Search110
A Vision-Guided Semantic-Group Network (VGSG) is proposed for text-based person search to extract well-aligned fine-grained visual and textual features and a relational knowledge transfer is designed to adaptively propagate information of the vision-guided textual features to semantic-group textual features.
- A Closer Look at Few-shot Image Generation97
Extensive experiments show that the proposed DCL brings visually pleasant quality and state-of-the-art quantitative performance, while leading to a slower diversity-degrading generator during adaptation, the method is still plenty of room to further slow down diversity degradation.
- 94
- Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation88
This work proposes to de-couple video-level referring expression understanding into static and motion perception, with a specific emphasis on enhancing temporal comprehension, and introduces an expression-decoupling module to make static cues and motion cues perform their distinct role.
- Region Generation and Assessment Network for Occluded Person Re-Identification88
A Region Generation and Assessment Network (RGANet) to effectively and efficiently detect the human body regions and highlight the important regions is proposed and extensive experimental results demonstrate the superiority of RGANet against state-of-the-art methods.
- 88
- Prototype Adaption and Projection for Few- and Zero-Shot 3D Point Cloud Semantic Segmentation87
A Query-Guided Prototype Adaption (QGPA) module to adapt the prototype from support point clouds feature space to query point cloud feature space is proposed and a semantic-visual projection model is proposed to bridge the semantic and visual spaces.
- 87
- OVTrack: Open-Vocabulary Multiple Object Tracking86
OVTrack is developed, an open-vocabulary tracker that is capable of tracking arbitrary object classes and its design is based on two key ingredients, leveraging vision-language models for both classification and association via knowledge distillation and a data hallucination strategy for robust appearance feature learning from denoising diffusion probabilistic models.
- Self-regularized prototypical network for few-shot semantic segmentation85
The proposed SRPNet extracts class-specific prototype representations from support images and generates segmentation masks for query images by a distance metric - the fidelity and achieves new state-of-art performance on 1-shot and 5-shot segmentation benchmarks.
- Bi-Directional Dermoscopic Feature Learning and Multi-Scale Consistent Decision Fusion for Skin Lesion Segmentation85
A novel bi-directional dermoscopic feature learning (biDFL) framework to model the complex correlation between skin lesions and their informative context and a multi-scale consistent decision fusion (mCDF) that is capable of selectively focusing on the informative decisions generated from multiple classification layers is proposed.
- Multi-Modal Mutual Attention and Iterative Interaction for Referring Image Segmentation84
The problem of referring image segmentation that aims to generate a mask for the object specified by a natural language expression is addressed and Iterative Multi-modal Interaction (IMI) is proposed to allow continuous and in-depth interactions between language and vision features.
- 83
- MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes74
This work presents MOSEv2, a significantly more challenging dataset designed to further advance VOS methods under real-world conditions, and benchmark 20 representative VOS methods under 5 different settings, highlighting that current VOS methods still fall short under real-world complexities.
- A Survey of Multimodal-Guided Image Editing with Text-to-Image Diffusion Models73
A comprehensive review of multimodal-guided image editing techniques that leverage T2I diffusion models, and proposes a unified framework to formalize the editing process, categorizing it into two primary algorithm families.
- Instance-Specific Feature Propagation for Referring Segmentation72
This work proposes a novel framework that simultaneously detects the target-of-interest via feature propagation and generates a fine-grained segmentation mask and outperforms previous state-of theart methods on all three RefCOCO series datasets.
- Federated Incremental Semantic Segmentation71
A Forgetting-Balanced Learning (FBL) model is proposed to address heterogeneous forgetting on old classes from both intra-client and interclient aspects to address catastrophic forgetting in Federated learning-based semantic segmentation.
- Duolando: Follower GPT with Off-Policy Reinforcement Learning for Dance Accompaniment70
A GPT-based model is proposed, Duolando, which autoregressively predicts the subsequent tokenized motion conditioned on the coordinated information of the music, the leader's and the follower's movements, and devise an off-policy reinforcement learning strategy that allows the model to explore viable trajectories from out-of-distribution samplings, guided by human-defined rewards.
- MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation69
This paper proposes a large-scale multi-modal dataset for referring motion expression video segmentation, focusing on segmenting and tracking target objects in videos based on language description of objects’ motions, and introduces MeViS, a dataset containing 33,072 human-annotated motion expressions in both text and audio.
- Towards Robust Referring Image Segmentation66
This work proposes a new formulation of RIS, named Robust Referring Image Segmentation (R-RIS), which considers the negative sentence inputs besides the regular positive text inputs, and proposes a new transformer-based model, called RefSegformer, with a token-based vision and language fusion module.
- Few-Shot Segmentation With Optimal Transport Matching and Message Flow65
This work argues that every support pixel’s information is desired to be transferred to all query pixels and proposes a Correspondence Matching Network (CMNet) with an Optimal Transport Matching module to mine out the correspondence between the query and support images.
- 65
- Global Knowledge Calibration for Fast Open-Vocabulary Segmentation64
A core idea of preserving the generalizable representation when fine-tuning on known classes is proposed, and a text diversification strategy that generates a set of synonyms for each training category is introduced, which prevents the learned representation from collapsing onto specific known category names.
- PhraseClick: Toward Achieving Flexible Interactive Segmentation by Phrase and Click64
The proposed multi-modal phrase+click approach achieves new state-of-the-art performance on interactive segmentation by employing phrase expressions as another interaction input to infer the attributes of target object.
- SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process57
A model-agnostic solution called SegRefiner is proposed, which offers a novel perspective on segmentation refinement as a data generation process by interpreting segmentation refinement as a data generation process, and which outperforms previous model-agnostic refinement methods by a significant margin.
- Primitive Generation and Semantic-Related Alignment for Universal Zero-Shot Segmentation55
This work introduces a generative model to synthesize features for unseen categories, which links semantic and visual spaces as well as addressing the issue of lack of unseen training data.
- Meta Navigator: Search for a Good Adaptation Policy for Few-shot Learning54
Inspired by the recent success in Automated Machine Learning literature, this paper presents Meta Navigator, a framework that attempts to solve the aforementioned limitation in few-shot learning by seeking a higher-level strategy and proffer to automate the selection from various few- shot learning designs.
- 53
- Expediting Large-Scale Vision Transformer for Dense Prediction Without Fine-Tuning52
This work presents two non-parametric operators specialized for dense prediction tasks, a token clustering layer to decrease the number of tokens for expediting and a token reconstruction layer to increase the number of tokens for recovering high-resolution.
- Knowledge-aware deep framework for collaborative skin lesion segmentation and melanoma recognition50
A novel knowledge-aware deep framework that incorporates some clinical knowledge into collaborative learning of two important melanoma diagnosis tasks, i.e., skin lesion segmentation and melanoma recognition is proposed.
- GREC: Generalized Referring Expression Comprehension48
This study introduces a new benchmark termed as Generalized Referring Expression Comprehension (GREC), which extends the classic REC by permitting expressions to describe any number of target objects, and builds the first large-scale GREC dataset named gRefCOCO.
- Distilling Knowledge From Object Classification to Aesthetics Assessment48
This work proposes to distill knowledge on semantic patterns for a vast variety of image contents from multiple pre-trained object classification (POC) models to an IAA model, expecting the combination of multiple POC models can provide sufficient knowledge on various image contents to easier learn to relate various distinct contents to a limited number of aesthetic labels.
- 47
- Learning Local and Global Temporal Contexts for Video Semantic Segmentation47
A Coarse-to-Fine Feature Mining (CFFM) technique to learn a unified presentation of LTC, and a CFFM++ by additionally learning GTC from the whole video to further exploit more temporal contexts.
- 42
- LCReg: Long-tailed image classification with Latent Categories based Recognition41
The proposed Latent Categories based long-tail Recognition (LCReg) method learns a set of class-agnostic latent features shared by both head and tail classes, and uses semantic data augmentation on the latent features to implicitly increase the diversity of the training sample.
- 41
- Betrayed by Captions: Joint Caption Grounding and Generation for Open Vocabulary Instance Segmentation40
This work devise a joint Caption Grounding and Generation (CGG) framework, which incorporates a novel grounding loss that only focuses on matching object nouns to improve learning efficiency and introduces a caption generation head that enables additional supervision and contextual modeling as a complementation to the grounding loss.
- 39
- DeepDeblur: text image recovery from blur to sharp38
This paper presents a deep network with 20 layers to cope with text image blur, and presents a novel network structure with Sequential Highway Connections (SHC) that is leveraged to gain superior convergence.
- 36
- Gradient-Semantic Compensation for Incremental Semantic Segmentation35
A step-aware gradient compensation that can balance forgetting paces of previously seen classes by re-weighting gradient back-propagation is developed and a soft-sharp semantic relation distillation is proposed to distill consistent inter-class semantic relations via soft labels for alleviating catastrophic forgetting from the semantic aspect.
- Mask-Free Video Instance Segmentation32
This work proposes MaskFreeVIS, achieving highly competitive VIS performance, while only using bounding box annotations for the object state, by introducing the Temporal KNN-patch Loss (TK-Loss), providing strong mask supervision without any labels.
- ReferSplat: Referring Segmentation in 3D Gaussian Splatting31
ReferSplat is introduced, a framework that explicitly models 3D Gaussian points with natural language expressions in a spatially aware paradigm that achieves state-of-the-art performance on both the newly proposed R3DGS task and 3D open-vocabulary segmentation benchmarks.
- RefMask3D: Language-Guided Transformer for 3D Referring Segmentation31
The proposed RefMask3D achieves new state-of-the-art performance on 3D referring segmentation, 3D visual grounding, and also 2D referring image segmentation and outperforms previous state-of-the-art method by a large margin on the challenging ScanRefer dataset.
- A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation29
This survey provides a comprehensive overview of recent progress in 3DGS applications, categorizing 3DGS applications into three foundational tasks: segmentation, editing, and generation, alongside additional functional applications built upon or tightly coupled with these foundational capabilities.
- Transferable Adversarial Attacks on SAM and Its Downstream Models29
This paper explores the feasibility of adversarial attacking various downstream models fine-tuned from the segment anything model (SAM), by solely utilizing the information from the open-sourced SAM, and proposes a universal meta-initialization (UMI) algorithm to extract the intrinsic vulnerability inherent in the foundation model.
- Semantic-Promoted Debiasing and Background Disambiguation for Zero-Shot Instance Segmentation29
D2Zero with Semantic-Promoted Debiasing and Background Disambiguation is proposed to enhance the performance of Zero-shot instance segmentation and significantly outperform previous state-of-the-art methods by a large margin.
- PrimitiveNet: decomposing the global constraints for referring segmentation28
A PrimitiveNet is proposed to decompose the difficult global constraints into a set of simple primitives that represent only simple semantic meanings and outperforms current state-of-the-art referring segmentation methods on three RefCOCO datasets.
- 27
- 3D-GRES: Generalized 3D Referring Expression Segmentation25
The Multi-Query Decoupled Interaction Network (MDIN) is proposed, designed to break down multi-object segmentation tasks into simpler, individual segmentations, charting a new path for intricate multi-object 3D scene comprehension.
- XOV-Action: Toward Generalizable Open-Vocabulary Action Recognition24
This work contributes a novel model named XOV-Action, which first proposes to capture diverse action-related concepts by learning diversified elaboration representations, which enables better generalization to open-set action categories and improves the generalization in unseen video domains.
- Continual LLaVA: Continual Instruction Tuning in Large Vision-Language Models24
This work proposes a new benchmark for COntinuAl inStruction Tuning on LVLMs (COAST), which encompasses the aforementioned domain-incremental, capability-incremental, and dataset-incremental configurations and proposes Continual LLaVA, a rehearsal-free method tailored for continual instruction tuning in LVLMs.
- 23
- PointCVaR: Risk-Optimized Outlier Removal for Robust 3D Point Cloud Classification23
This paper introduces an innovative point outlier cleansing method that harnesses the power of downstream classification models and recast the outlier removal process as an optimization problem, named PointCVaR.
- Towards Enhancing Fine-grained Details for Image Matting23
A novel term in loss function and a trimap generation method are proposed to improve the model’s robustness to the trimaps and show that the method outperforms previous start-of-the-art methods on the Composition-1k dataset.
- 22
- 21
- Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing19
Theoretically, it is proved that DRS guarantees a tight ${\ell_2}$ certified robustness radius for the original input and revealed that DRS attains a superior upper bound on the ${\ell_2}$ robustness radius, which decreases proportionally at a rate of $(1/\sqrt m + 1/\sqrt n )$ with $m+n=d).
- 18
- Exploiting Temporal State Space Sharing for Video Semantic Segmentation17
A Temporal Video State Space Sharing (TV3S) architecture to leverage Mamba state space models for temporal feature sharing, which features a selective gating mechanism that efficiently propagates relevant information across video frames, eliminating the need for a memory-heavy feature pool.
- Improving Video Instance Segmentation via Temporal Pyramid Routing17
A Temporal Pyramid Routing strategy to conditionally align and conduct pixel-level aggregation from a feature pyramid pair of two adjacent frames is proposed, which is a light-weight and plug-and-play module and can be easily applied to existing instance segmentation methods.
- Towards Omnimodal Expressions and Reasoning in Referring Audio-Visual Segmentation16
OmniAVS is proposed, a new dataset containing 2,104 videos and 61,095 multimodal referring expressions and Omnimodal Instructed Segmentation Assistant (OISA) is introduced, to address the challenges of multimodal reasoning and finegrained understanding of audiovisual content in OmniAVS.
- Deep Geometrized Cartoon Line Inbetweening16
A new approach, AnimeInbet, is proposed, which geometrizes raster line drawings into graphs of endpoints and reframes the inbetweening task as a graph fusion problem with vertex repositioning, which can effectively capture the sparsity and unique structure of line drawings while preserving the details during inbetweening.
- Free-Form Motion Control: Controlling the 6D Poses of Camera and Objects in Video Generation15
A Synthetic Dataset for Free-Form Motion Control (SynFMC) is introduced, which can control the 6D poses of objects and camera independently or simultaneously, producing high-fidelity videos and outperforms previous methods across multiple scenarios.
- Spatial feature mapping for 6DoF object pose estimation15
This work aims to estimate 6Dof (6D) object pose in background clutter by utilizing the spatial structure for better tackling this challenging task and addresses the problem of rotation symmetry ambiguity for objects.
- 15
- 14
- 14
- 14
- 14
- AnyI2V: Animating Any Conditional Image with Motion Control13
This paper presents a new generation of T2V synthesis methods that combine text-tovideo (T2V) and image-to-video (I2V) synthesis with dynamic motion signals and flexible spatial constraints.
- IAP: Improving Continual Learning of Vision-Language Models via Instance-Aware Prompting12
This paper proposes an Instance-Aware Gated Prompting (IA-GP) strategy, which enhances adaptation to new tasks while mitigating forgetting by adaptively assigning prompts across transformer layers at the instance level and improves the task adaptation process by determining an accurate task-label-related confidence score for each instance.
- Segment Anything with Precise Interaction11
Pi-SAM possesses a strong perception capability for the extremely fine details in high-resolution images, enabling it to generate high-precision segmentation masks and ensures highly efficient model fine-tuning to achieve the above performance.
- 10
- Visual Reasoning Tracer: Object-Level Grounded Reasoning Benchmark10
The Visual Reasoning Tracer task is introduced, which requires models to not only localize the target object but also explicitly predict the intermediate objects that form the reasoning path, and reveals that while existing models often produce the correct final output, they struggle to ground their intermediate reasoning.
- 10
- 9
- GREx: Generalized Referring Expression Segmentation, Comprehension, and Generation8
Three new benchmarks called Generalized Referring Expression Segmentation (GRES), Comprehension (GREC), and Generation (GREG), collectively denoted as GREx, which extend the classic REx to allow expressions to identify an arbitrary number of objects are introduced.
- 8
- 8
- MOVE: Motion-Guided Few-Shot Video Object Segmentation8
This work introduces MOVE, a large-scale dataset specifically designed for motion-guided FSVOS, and comprehensively evaluates 6 state-of-the-art methods from 3 different related tasks across 2 experimental settings, demonstrating that this approach achieves superior performance in few-shot motion understanding.
- PECTP: Parameter-Efficient Cross-Task Prompts for Incremental Vision Transformer8
A Parameter-Efficient Cross-Task Prompt (PECTP) framework with Prompt Retention Module (PRM) and classifier Head Retention Module (HRM) and HRM to inherit old knowledge in the previously learned classifier heads to facilitate the cross-task prompts’ generalization ability.
- Primitive3D: 3D Object Dataset Synthesis from Randomly Assembled Primitives8
This work proposes a cost-effective method for automatically generating a large amount of 3D objects with annotations, and proposes a dataset distillation strategy to remove redundant samples regarding a target dataset.
- Exploiting independent query information for few-shot image segmentation7
This work proposes a prior extractor to learn the query information from the unlabeled images with the proposed global–local contrastive learning and generates the prior region maps for query images, which locate the objects, as guidance to perform cross-interaction with support features.
- 6
- 6
- [Algorithm for recognizing the markers in human motion detection].6
An algorithm for recognizing the markers in human motion detection is proposed and the result of experiments shows that the algorithm can recognize the positions of the markers at a relatively higher accuracy and speed.
- 5
- Evaluating SAM2 for Video Semantic Segmentation5
This paper explores the extension of SAM2 for VSS, focusing on two primary approaches and highlighting firsthand observations and common challenges faced during this process, and suggests that leveraging SAM2 enhances overall performance in VSS, primarily due to its precise predictions of object boundaries.
- 5
- Long-tailed Recognition by Learning from Latent Categories5
This work proposes to learn a set of class-agnostic latent features shared among the head and tail classes and implicitly enrich the training sample diversity via applying semantic data augmentation to the latent features.
- Learning Trimaps via Clicks for Image Matting4
This work introduces Click2Trimap, an interactive model that is capable of predicting high-quality trimaps and alpha mattes with minimal user click inputs and proposes a powerful iterative three-class training strategy and a dedicated simulation function, making Click2Trimap exhibit versatility across various scenarios.
- Decoupling with Entropy-based Equalization for Semi-Supervised Semantic Segmentation4
This work proposes a Decoupled Semi-Supervise Semantic Segmentation (DeS4) framework based on the teacher-student model, and proposes a non-learnable prototype-based segmentation head to regularize the category representation distribution consistency and perform a better connection between the teacher model and the student model.
- Hierarchical Visual Prompt Learning for Continual Video Instance Segmentation3
A novel Hierarchical Visual Prompt Learning (HVPL) model is developed that overcomes catastrophic forgetting of previous categories from both frame-level and video-level perspectives and proves to be more effective than baseline approaches.
- 3
- 2
- Progressive Scaling Visual Object Tracking2
DT-Training is introduced, a progressive scaling framework that integrates small teacher transfer and dual-branch alignment to maximize model potential and consistently outperforms state-of-the-art methods across multiple benchmarks.
- 2
- 2
- 2
- 2
- NeMI: Unifying Neural Radiance Fields with Multiplane Images for Novel View Synthesis2
The NeMI is a general two-dimensional and imageconditioned extension of NeRF, and a continuous depth generalization of MPI, which combines Neural radiance fields with Multiplane Images to perform novel view synthesis and depth estimation via dense 3D reconstruction from a single image.
- Object 6D pose estimation with non-local attention2
A concise and efficient network that integrates 6D object pose parameter estimation into the object detection framework is proposed and for more robust estimation to occlusion, a nonlocal self-attention module is introduced.
- SAM3-DMS: Decoupled Memory Selection for Multi-target Video Segmentation of SAM31
This work proposes SAM3-DMS, a training-free decoupled strategy that utilizes fine-grained memory selection on individual objects that achieves robust identity preservation and tracking stability and becomes more pronounced with increased target density.
- Efficient image dehazing with synergic expert modulation1
A synergic expert modulation network is constructed by inserting SEM-based building blocks into the U-Net architecture to increase efficiency and achieve state-of-the-art performance on multiple datasets for the image dehazing task while incurring lower computational costs.
- Open-Set Anomaly Segmentation in Complex Scenarios1
This paper introduces the ComSAmy, a Complex Scenarios Anomaly segmentation benchmark, and proposes a novel energy-entropy learning (EEL) strategy that integrates the complementary information from energy and entropy to bolster the robustness of anomaly segmentation under complex open-world environments.
- Crafting Your Evolving Dreams: Concept-Incremental Versatile Customization1
This work develops a novel Continually Customizable Diffusion Model (CCDM), enabling users to perform concept-incremental versatile customization, and proposes a controllable regional context synthesis strategy that performs multi-concept composition in alignment with user-provided conditions.
- Event-Aware Instructed Assistant for Referring Video Segmentation1
EVIS, an Event-Aware Video Instructed Segmentation Assistant, is introduced, which utilizes text-guided Event Queries to partition a video into simple events, extracting event-aware visual-text features to achieve a hierarchical understanding of the video.
- 1
- 1
- 1
- 1
- AdAM: Few-Shot Image Generation via Adaptation-Aware Kernel Modulation1
It is revealed that under setups which assumption of close proximity between source and target domains is relaxed, many existing state-of-the-art (SOTA) methods which consider only source domain in knowledge preserving perform no better than a baseline method.
- Learning-Based Biharmonic Augmentation for Point Cloud Classification1
Biharmonic Augmentation is a novel and efficient data augmentation technique that diversifies point cloud data by imposing smooth non-rigid deformations on existing 3D structures and AdvTune, an advanced online augmentation system that integrates adversarial training is presented.
- 1
- –
- –
- Instance-Adaptive Routing for Object Re-Identification with Heterogeneous Experts–
This work proposes an end-to-end framework in which a multimodal LLM serves as the routing policy for ReID, and introduces a non-parametric variant that performs expert selection via retrieval-augmented expert descriptors, enabling new tools to be integrated without retraining.
- –
- –
- –
- –
- Cross-Domain Knowledge Distillation for Low-Resolution Human Pose Estimation–
A novel cross-domain knowledge distillation (CDKD) framework is proposed that adopts a scale-adaptive projector ensemble (SAPE) module to spatially align feature maps between models of varying input resolutions and construct a cross-class alignment (CCA) module to solve the problem of the mismatch of class numbers.
- –
- –
- –
- –
- –
- –
- –
- –
- A study on frequency-time domain transformation through tracing-assisted dual microring integrated system–
High-resolution and high-sensitivity transformation from frequency domain to time domain is demonstrated by a tracing-assisted dual microring integrated system promising for applications in frequency follower, chemical or biological sensing in environmental monitoring.
- Real-time Label-free Monitoring of Protozoa using Micro Opto-fluidic System and Image Classification–
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.