The success of 3DGS in generative and editing applications has sparked growing interest in 3DGS-based style transfer. However, current methods still face two major challenges: (1) multi-view inconsistency often leads to style conflicts, resulting in appearance smoothing and distortion; and (2) heavy reliance on VGG features, which struggle to disentangle style and content from style images, often causing content leakage and excessive stylization. To tackle these issues, we introduce FantasyStyle, a 3DGS-based style transfer framework, and the first to rely entirely on diffusion model distillation. It comprises two key components: (1) Multi-View Frequency Consistency. We enhance cross-view consistency by applying a 3D filter to multi-view noisy latent, selectively reducing low-frequency components to mitigate stylized prior conflicts. (2) Controllable Stylized Distillation. To suppress content leakage from style images, we introduce negative guidance to exclude undesired content. In addition, we identify the limitations of Score Distillation Sampling and Delta Denoising Score in 3D style transfer and remove the reconstruction term accordingly. Building on these insights, we propose a controllable stylized distillation that leverages negative guidance to more effectively optimize the 3D Gaussians. Extensive experiments demonstrate that our method consistently outperforms state-of-the-art approaches, achieving higher stylization quality and visual realism across various scenes and styles.

Object re-identification (ReID) performs well on standard benchmarks, yet real deployments are often modality-mixed, where queries arise from heterogeneous sensors and conditions. In this setting, modality gaps and environmental shifts can substantially degrade retrieval accuracy, and a single unified model rarely performs uniformly well across modalities. We therefore study instance-adaptive expert routing for ReID, where a router selects the most suitable expert from a heterogeneous toolbox for a given query and a fixed gallery. We propose an end-to-end framework in which a multimodal LLM serves as the routing policy. The router is trained first with semantic preference supervision, where instance-level expert preferences are derived from retrieval outcomes using a reproducible protocol, and then optimized with policy-gradient learning using downstream retrieval rewards. To support continual expansion of the expert set, we further introduce a non-parametric variant that performs expert selection via retrieval-augmented expert descriptors, enabling new tools to be integrated without retraining. Experiments on cross-modal and cross-domain benchmarks demonstrate consistent improvements over unified ReID models and fixed-expert baselines.Our project is publicly available at the GitHub repository.

Referring video object segmentation (RVOS) is an emerging task that aims to segment the text-referred objects in the given video sequence. This capability plays a critical role in some real-world safety-critical applications such as autonomous driving. However, advanced RVOS models predominantly leverage deep neural networks that are inherently vulnerable to adversarial perturbations, which raises serious safety concerns. Although some studies have explored adversarial attacks on video object segmentation (VOS), the robustness and security of RVOS models against such attacks remain insufficiently investigated. This work thus, for the first time, comprehensively investigates the adversarial robustness of RVOS models. Distinct from other VOS tasks, RVOS is more challenging due to its multi-modal nature and high dependence on spatial-temporal information. Considering that, we propose a cross-prompt Multimodal attack with Inter-Clip Momentum (xM-ICM) to effectively mislead RVOS models under both white-box and black-box scenarios. The proposed xM jointly corrupts visual and textual embeddings and integrates a cross-prompt strategy during iterative optimization to enhance generalization across diverse linguistic queries. The ICM module harnesses the spatial-temporal dependencies across sequence clips via two momentum banks to preserve the perturbation coherence throughout the whole video and stabilize the adversarial optimization. Experimental results on three benchmarks and five prevalent RVOS models demonstrate the superior white-box attack performance and strong black-box transferability of our proposed method.

Existing referring video segmentation methods often treat a video as a single event consisting of multiple images, overlooking the fact that a video typically contains multiple distinct events. Under such a mechanism, the model needs to directly understand all the complex content in the video and text, which can easily lead to confusion and hallucinations. To address this issue, we propose to decompose a video to a set of simple events by learnable Event Query, and understand complex video content in an event-by-event, easy-to-understand manner. This is based on the observation that natural language expressions often divide a video into distinct, text-related segments, each representing a separate event within a compound event. We introduce EVIS, an Event-Aware Video Instructed Segmentation Assistant, 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. Additionally, we propose Object-Pixel-Hybrid Learning, which enables the MLLMs to track targets in long-term videos by integrating fine-grained pixel features with prior object queries. Extensive experimental results on 5 public benchmarks demonstrate EVIS's strong performance in addressing the referring video segmentation task. Code and trained models will be publicly released.

Referring Video Object Segmentation (RVOS) aims to segment the target objects specified in human instructions. Previous approaches typically rely on explicit human instructions that contain target categories or salient appearance descriptions. These approaches tend to fail when the instructions require temporal video understanding and complex relational reasoning. In this work, we present RViSeg, a reasoning-centric video object segmentation model that leverages the reasoning capability of Multi-modal Large Language Models (MLLM) to handle complex queries. The primary challenge lies in enabling MLLM to perform efficient pixel-level video perception. To tackle this challenge, we introduce a novel Spatial Token Merge (STM) module that consolidates lengthy video tokens into compact region-level clusters, while preserving essential spatial details. This structured representation enables MLLM to infer user intention by interleaving spatial and temporal visual information. Furthermore, we propose a Query-based Target Retrieval (QTR) module that utilizes learnable tokens as the target identity for mask prediction. By propagating these instance-specific tokens both intra-clip and inter-clip, our RViSeg effectively encodes object motion, ensuring spatio-temporal consistency in segmentation results. To facilitate training and evaluation, we construct InstructVideo, a single- and multiple-object reasoning video segmentation benchmark. Comprehensive experiments demonstrate the effectiveness of the proposed components.

Instance segmentation algorithms in remote sensing are typically based on conventional methods, limiting their application to seen scenarios and closed-set predictions. In this work, we propose a novel task called zero-shot remote sensing instance segmentation, aimed at identifying aerial objects that are absent from training data. Challenges arise when classifying aerial categories with high inter-class similarity and intra-class variance. Besides, the domain gap between vision-language models’ pretraining datasets and remote sensing datasets hinders the zero-shot capabilities of the pretrained model when it is directly applied to remote sensing images. To address these challenges, we propose a Zero-Shot Remote Sensing Instance Segmentation framework, dubbed ZoRI. Our approach features a discrimination-enhanced classifier that uses refined textual embeddings to increase the awareness of class disparities. Instead of direct fine-tuning, we propose a knowledge-maintained adaptation strategy that decouples semantic-related information to preserve vision-language alignment while adjusting features to capture remote sensing domain-specific visual cues. Additionally, we introduce a prior-injected prediction with cache bank of aerial visual prototypes to supplement the semantic richness of text embeddings and seamlessly integrate aerial representations, adapting to the remote sensing domain. We establish new experimental protocols and benchmarks, and extensive experiments demonstrate that ZoRI achieves the state-of-art performance on the zero-shot remote sensing instance segmentation task.

In this work, we address the challenging task of Generalized Referring Expression Comprehension (GREC). Compared to the classic Referring Expression Comprehension (REC) that focuses on single-target expressions, GREC extends the scope to a more practical setting by further encompassing no-target and multi-target expressions. Existing REC methods face challenges in handling the complex cases encountered in GREC, primarily due to their fixed output and limitations in multi-modal representations. To address these issues, we propose a Hierarchical Alignment-enhanced Adaptive Grounding Network (HieA2G) for GREC, which can flexibly deal with various types of referring expressions. First, a Hierarchical Multi-modal Semantic Alignment (HMSA) module is proposed to incorporate three levels of alignments, including word-object, phrase-object, and text-image alignment. It enables hierarchical cross-modal interactions across multiple levels to achieve comprehensive and robust multi-modal understanding, greatly enhancing grounding ability for complex cases. Then, to address the varying number of target objects in GREC, we introduce an Adaptive Grounding Counter (AGC) to dynamically determine the number of output targets. Additionally, an auxiliary contrastive loss is employed in AGC to enhance object-counting ability by pulling in multi-modal features with the same counting and pushing away those with different counting. Extensive experimental results show that HieA2G achieves new state-of-the-art performance on the challenging GREC task and also the other 4 tasks, including REC, Phrase Grounding, Referring Expression Segmentation (RES), and Generalized Referring Expression Segmentation (GRES), demonstrating the remarkable superiority and generalizability of the proposed HieA2G.

Few-shot point cloud semantic segmentation aims to accurately segment "unseen" new categories in point cloud scenes using limited labeled data. However, pretraining-based methods not only introduce excessive time overhead but also overlook the local structure representation among irregular point clouds. To address these issues, we propose a pretraining-free local structure fitting network for few-shot point cloud semantic segmentation, named TaylorSeg. Specifically, inspired by Taylor series, we treat the local structure representation of irregular point clouds as a polynomial fitting problem and propose a novel local structure fitting convolution, called TaylorConv. This convolution learns the low-order basic information and high-order refined information of point clouds from explicit encoding of local geometric structures. Then, using TaylorConv as the basic component, we construct two variant of TaylorSeg: a non-parametric TaylorSeg-NN and a parametric TaylorSeg-PN. The former can achieve performance comparable to existing parametric models without pretraining. For the latter, we equip it with an Adaptive Push-Pull (APP) module to mitigate the feature distribution differences between the query set and the support set. Extensive experiments validate the effectiveness of the proposed method. Notably, under the 2-way 1-shot setting, TaylorSeg-PN achieves improvements of +2.28% and +4.37% mIoU on the S3DIS and ScanNet datasets respectively, compared to the previous state-of-the-art methods.

While existing pre-training-based methods have enhanced point cloud model performance, they have not fundamentally resolved the challenge of local structure representation in point clouds. The limited representational capacity of pure point cloud models continues to constrain the potential of cross-modal fusion methods and performance across various tasks. To address this challenge, we propose a Dynamic Acoustic Field Fitting Network (DAF-Net), inspired by physical acoustic principles. Specifically, we represent local point clouds as acoustic fields and introduce a novel Acoustic Field Convolution (AF-Conv), which treats local aggregation as an acoustic energy field modeling problem and captures fine-grained local shape awareness by dividing the local area into near field and far field. Furthermore, drawing inspiration from multi-frequency wave phenomena and dynamic convolution, we develop the Dynamic Acoustic Field Convolution (DAF-Conv) based on AF-Conv. DAF-Conv dynamically generates multiple weights based on local geometric priors, effectively enhancing adaptability to diverse geometric features. Additionally, we design a Global Shape-Aware (GSA) layer incorporating EdgeConv and multi-head attention mechanisms, which combines with DAF-Conv to form the DAF Block. These blocks are then stacked to create a hierarchical DAFNet architecture. Extensive experiments demonstrate that DAFNet significantly outperforms existing methods across multiple tasks.

Sequential grounding in 3D point clouds (SG3D) refers to locating sequences of objects by following text instructions for a daily activity with detailed steps. Current 3D visual grounding (3DVG) methods treat text instructions with multiple steps as a whole, without extracting useful temporal information from each step. However, the instructions in SG3D often contain pronouns such as "it", "here" and "the same" to make language expressions concise. This requires grounding methods to understand the context and retrieve relevant information from previous steps to correctly locate object sequences. Due to the lack of an effective module for collecting related historical information, state-of-the-art 3DVG methods face significant challenges in adapting to the SG3D task. To fill this gap, we propose GroundFlow -- a plug-in module for temporal reasoning on 3D point cloud sequential grounding. Firstly, we demonstrate that integrating GroundFlow improves the task accuracy of 3DVG baseline methods by a large margin (+7.5\% and +10.2\%) in the SG3D benchmark, even outperforming a 3D large language model pre-trained on various datasets. Furthermore, we selectively extract both short-term and long-term step information based on its relevance to the current instruction, enabling GroundFlow to take a comprehensive view of historical information and maintain its temporal understanding advantage as step counts increase. Overall, our work introduces temporal reasoning capabilities to existing 3DVG models and achieves state-of-the-art performance in the SG3D benchmark across five datasets.

We introduce Referring 3D Gaussian Splatting Segmentation (R3DGS), a new task that aims to segment target objects in a 3D Gaussian scene based on natural language descriptions, which often contain spatial relationships or object attributes. This task requires the model to identify newly described objects that may be occluded or not directly visible in a novel view, posing a significant challenge for 3D multi-modal understanding. Developing this capability is crucial for advancing embodied AI. To support research in this area, we construct the first R3DGS dataset, Ref-LERF. Our analysis reveals that 3D multi-modal understanding and spatial relationship modeling are key challenges for R3DGS. To address these challenges, we propose ReferSplat, a framework that explicitly models 3D Gaussian points with natural language expressions in a spatially aware paradigm. ReferSplat achieves state-of-the-art performance on both the newly proposed R3DGS task and 3D open-vocabulary segmentation benchmarks. Dataset and code are available at https://github.com/heshuting555/ReferSplat.

The domain gap between pretraining data (e.g., ImageNet, LUPerson) and downstream ReID datasets often leads to suboptimal performance when directly fine-tuning pretrained models. While existing methods attempt to bridge this gap by incorporating additional modalities (e.g., text, 3D data) or visual cues (e.g., pose, body masks), these approaches introduce two key limitations: (1) they may distract the model with irrelevant factors like background clutter or clothing variations, and (2) they inevitably increase computational overhead during inference. To address these issues, we propose the Weak Saliency Feedback Transformer (WSFFormer), inspired by the feedback mechanisms in biological visual systems. Unlike traditional one-way feature propagation, WSFFormer employs an adaptive feedback loop during training to enhance low-response regions, enabling the model to capture richer and more discriminative features. The WSFFormer introduces three key components: (1) The Lateral Feedback Module (LFM) mimics retinal lateral inhibition by adaptively suppressing high-response regions and amplifying weak discriminative features, forcing attention on subtle details; (2) The Progressive Feedback Module (PFM) refines feedback through deep-to-shallow closed-loop propagation, blending high-level semantics with spatial details; (3) The Feedback Sensitive Entropy Loss (FSE Loss) optimizes target-domain adaptation by quantifying divergence between forward and feedback-corrected features. Experiments on holistic/occluded ReID benchmarks show WSFFormer outperforms ViT/Swin-based SOTA methods without extra inference cost.

The reasoning segmentation task involves segmenting objects within an image by interpreting implicit user instructions. Despite significant advancements made by existing approaches, they remain constrained by low perceptual resolution, as visual encoders are typically pre-trained at lower resolutions. Furthermore, simply interpolating the positional embeddings of visual encoders to enhance perceptual resolution yields only marginal performance improvements while incurring substantial computational costs. To address this, we propose HRSeg, an efficient model with high-resolution fine-grained perception. It features two key innovations: High-Resolution Perception (HRP) and High-Resolution Enhancement (HRE). The HRP module processes high-resolution images through cropping, integrating local and global features for multi-granularity quality. The HRE module enhances mask features by integrating fine-grained information from high-resolution images, refining their alignment with text features for precise segmentation. Extensive ablation studies validate the effectiveness of our modules, while comprehensive experiments on multiple benchmark datasets demonstrate HRSeg's superior performance. Code will be available at https://github.com/WeihuangLin/HRSeg.

While text-driven diffusion models demonstrate remarkable performance in image editing, the critical components of their text embeddings remain underexplored. The ambiguity and entanglement of these embeddings pose challenges for precise editing. In this paper, we provide a comprehensive analysis of text embeddings in Stable Diffusion XL, offering three key insights: (1) aug embedding ~. aug embedding is obtained by combining the pooled output of the final text encoder with the timestep embeddings. https://github.com/huggingface/diffusers retains complete textual semantics but contributes minimally to image generation as it is only fused via the ResBlocks. More text information weakens its local semantics while preserving most global semantics. (2) BOS and padding embedding do not contain any semantic information. (3) EOS holds the semantic information of all words and stylistic information. Each word embedding is important and does not interfere with the semantic injection of other embeddings. Based on these insights, we propose PSP (Prompt-Softbox-Prompt), a training-free image editing method that leverages free-text embedding. PSP enables precise image editing by modifying text embeddings within the cross-attention layers and using Softbox to control the specific area for semantic injection. This technique enables the addition and replacement of objects without affecting other areas of the image. Additionally, PSP can achieve style transfer by simply replacing text embeddings. Extensive experiments show that PSP performs remarkably well in tasks such as object replacement, object addition, and style transfer. Our code is available at https://github.com/yangyt46/PSP.

Point Cloud Few-Shot Semantic Segmentation (PC-FSS) aims to segment unknown categories in query samples using only a small number of annotated support samples. However, scene complexity and insufficient representation of local geometric structures pose significant challenges to PC-FSS. To address these issues, we propose a novel pre-training-free Visual Introspective Prototype Segmentation network (VIP-Seg). Specifically, we design a Visual Introspective Prototype (VIP) module that employs a multi-step reasoning approach to tackle intra-class diversity and domain gaps between support and query sets. The VIP module consists of a Prototype Enhancement Module (PEM) and a Prototype Difference Module (PDM), which work alternately to progressively refine prototypes. The PEM enhances prototype discriminability and reduces intra-class diversity, while the PDM learns common representations from the differences between query and support features, effectively eliminating semantic inconsistencies caused by domain gaps. To further reduce intra-class diversity and enhance point discriminative ability, we propose a Dynamic Power Convolution (DyPowerConv) that leverages learnable power functions to effectively capture local geometric structures and detailed features of point clouds. Extensive experiments on S3DIS and ScanNet demonstrate that our proposed VIP-Seg significantly outperforms current state-of-the-art methods, proving its effectiveness in PC-FSS tasks. Our code will be available at https://github.com/changshuowang/VIP-Seg .

Iterative imputation is a prevalent method for missing data imputation, where each feature is imputed iteratively by treating it as a target variable estimated from all other features. However, iterative imputation method suffers from two principal limitations: (1) it imposes a single parametric model form to impute all features, neglecting the potential for optimal models to vary among features, which risks model misspecification; and (2) it assumes every feature contains missing values, overlooking the potential presence of non-missing features, termed as oracle features, which are informative for imputation. To address these limitations, we propose kernel point imputation (KPI), a bi-level optimization framework for iterative missing data imputation. At the inner level, KPI adaptively learns the optimal model form for each feature within a reproducing kernel Hilbert space, addressing limitation (1). At the outer level, KPI utilizes oracle features as supervisory signals to iteratively refine the imputations, addressing limitation (2). Experiments demonstrate that KPI outperforms competitive imputation methods. Code is available at https://github.com/FMLYD/kpi.git.

Diagram question answering (DQA) is a challenging task that requires models to combine with domain-specific knowledge and reason over the diagrams to answer questions. Multimodal Large Language Models (MLLMs) have recently made notable strides in combining textual and visual information, emerging as a promising solution for addressing the DQA task. However, they still encounter challenges in deliberate multimodal reasoning over the fine-grained visual details of content-rich and knowledge-grounded diagrams. The tight interweaving of visual and textual reasoning for MLLMs is also susceptible to hallucinations. To overcome these limitations, we propose a Glance-then-Focus Multimodal Reasoning framework named GlFoMR for DQA, which features a flexible architecture for comprehensive visual and text interaction. Firstly, the diagram is parsed into a hierarchical structure spanning different granularities including isolated single-object, object-group, and whole-diagram. Subsequently, the Glance-Plan and Focus-Reason stages collaborate to decouple the complex reasoning process. Glance-Plan first generates a preliminary plan by glancing at the multimodal context, specifying sub-goals related to knowledge extraction, visual perception, and visual reasoning. Based on these sub-goals, Focus-Reason further integrates domain-specific knowledge and visual details to enable more deliberate reasoning. The parsed multi-granularity diagram information is seamlessly incorporated into the corresponding sub-goal achievement process, enhancing the perception and reasoning capabilities of MLLMs for better DQA performance. Extensive experimental results on four DQA datasets demonstrate that GlFoMR achieves substantial improvements, showcasing its potential to advance the development of multimodal reasoning.

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. Existing referring video segmentation datasets often focus on salient objects and use language expressions rich in static attributes, potentially allowing the target object to be identified in a single frame. Such datasets underemphasize the role of motion in both videos and languages. To explore the feasibility of using motion expressions and motion reasoning clues for pixel-level video understanding, we introduce MeViS, a dataset containing 33,072 human-annotated motion expressions in both text and audio, covering 8,171 objects in 2,006 videos of complex scenarios. We benchmark 15 existing methods across 4 tasks supported by MeViS, including 6 referring video object segmentation (RVOS) methods, 3 audio-guided video object segmentation (AVOS) methods, 2 referring multi-object tracking (RMOT) methods, and 4 video captioning methods for the newly introduced referring motion expression generation (RMEG) task. The results demonstrate weaknesses and limitations of existing methods in addressing motion expression-guided video understanding. We further analyze the challenges and propose an approach LMPM++ for RVOS/AVOS/RMOT that achieves new state-of-the-art results. Our dataset provides a platform that facilitates the development of motion expression-guided video understanding algorithms in complex video scenes.

Existing occluded person re-identification (re-ID) methods mainly learn limited visual information for occluded pedestrians from images. However, textual information, which can describe various human appearance attributes, is rarely fully utilized in the task. To address this issue, we propose a Text-guided Hierarchical Context Blending Network ( THCB-Net) for occluded person re-ID. Specifically, at the data level, informative multi-modal inputs are first generated to make full use of the auxiliary role of textual information and make image data have a strong inductive bias for occluded environments. At the feature expression level, we design a novel Hierarchical Context Blending (HCB) module that can adaptively integrate shallow appearance features obtained by CNNs and multi-scale semantic features from visual transformer encoder. At the model optimization level, a Multi-modal Feature Interaction (MFI) module is proposed to learn the multi-modal information of pedestrians from texts and images, then guide the visual transformer encoder and HCB module to further learn discriminative identity information for occluded pedestrians through Image-Multimodal Contrastive (IMC) learning. Extensive experiments on standard occluded person re-ID benchmarks demonstrate that the proposed THCB-Net outperforms state-of-the-art methods.

Referring video segmentation relies on natural language expressions to identify and segment objects, often empha-sizing motion clues. Previous works treat a sentence as a whole and directly perform identification at the video-level, mixing up static image-level cues with temporal motion cues. However, image-level features cannot well comprehend motion cues in sentences, and static cues are not crucial for temporal perception. In fact, static cues can sometimes interfere with temporal perception by overshadowing motion cues. In this work, we propose to de-couple video-level referring expression understanding into static and motion perception, with a specific emphasis on enhancing temporal comprehension. Firstly, we introduce an expression-decoupling module to make static cues and motion cues perform their distinct role, alleviating the issue of sentence embeddings overlooking motion cues. Secondly, we propose a hierarchical motion perception module to capture temporal information effectively across varying timescales. Furthermore, we employ contrastive learning to distinguish the motions of visually similar objects. These contributions yield state-of-the-art performance across five datasets, including a remarkable 9.2% J&F improvement on the challenging MeViS dataset. Code is available at https://github.conllheshuting555IDsHmp.

Tracking by natural language specification (TNL) aims to consistently localize a target in a video sequence given a linguistic description in the initial frame. Existing methodologies perform language-based and template-based matching for target reasoning separately and merge the matching results from two sources, which suffer from tracking drift when language and visual templates missalign with the dynamic target state and ambiguity in the later merging stage. To tackle the issues, we propose a joint multi-modal tracking framework with 1) a prompt modulation module to leverage the complementarity between temporal visual templates and language expressions, enabling precise and context-aware appearance and linguistic cues, and 2) a unified target decoding module to integrate the multi-modal reference cues and executes the integrated queries on the search image to predict the target location in an end-to-end manner directly. This design ensures spatio-temporal consistency by leveraging historical visual information and introduces an integrated solution, generating predictions in a single step. Extensive experiments conducted on TNL2K, OTB-Lang, LaSOT, and RefCOCOg validate the efficacy of our proposed approach. The results demonstrate competitive performance against state-of-the-art methods for both tracking and grounding. Code is available at https://github.com/twotw02/QueryNLT

3D referring segmentation is an emerging and challenging vision-language task that aims to segment the object described by a natural language expression in a point cloud scene. The key challenge behind this task is vision-language feature fusion and alignment. In this work, we propose RefMask3D to explore the comprehensive multi-modal feature interaction and understanding. First, we propose a Geometry-Enhanced Group-Word Attention to integrate language with geometrically coherent sub-clouds through cross-modal group-word attention, which effectively addresses the challenges posed by the sparse and irregular nature of point clouds. Then, we introduce a Linguistic Primitives Construction to produce semantic primitives representing distinct semantic attributes, which greatly enhance the vision-language understanding at the decoding stage. Furthermore, we introduce an Object Cluster Module that analyzes the interrelationships among linguistic primitives to consolidate their insights and pinpoint common characteristics, helping to capture holistic information and enhance the precision of target identification. The proposed RefMask3D achieves new state-of-the-art performance on 3D referring segmentation, 3D visual grounding, and also 2D referring image segmentation. Especially, RefMask3D outperforms previous state-of-the-art method by a large margin of 3.16% mIoU on the challenging ScanRefer dataset. Code is available at https://github.com/heshuting555/RefMask3D.

Arbitrary style transfer aims to render artistic features from a style reference onto an image while retaining its original content. Previous methods either focus on learning the holistic style from a specific artist or extracting instance features from a single artwork. However, they often fail to apply style elements uniformly across the entire image and lack adaptation to the style of different artworks. To solve these issues, our key insight is that the art genre has better generality and adaptability than the overall features of the artist. To this end, we propose a Dual-head Genre-instance Transformer (DGiT) framework to simultaneously capture the genre and instance features for arbitrary style transfer. To the best of our knowledge, this is the first work to integrate the genre features and instance features to generate a high-quality stylized image. Moreover, we design two contrastive losses to enhance the capability of the network to capture two style features. Our approach ensures the uniform distribution of the overall style across the stylized image while enhancing the details of textures and strokes in local regions. Qualitative and quantitative evaluations demonstrate that our approach exhibits superior visual quality and efficiency.

Person Re-identification (ReID) plays a more and more crucial role in recent years with a wide range of applications. Existing ReID methods are suffering from the challenges of misalignment and occlusions, which degrade the performance dramatically. Most methods tackle such challenges by utilizing external tools to locate body parts or exploiting matching strategies. Nevertheless, the inevitable domain gap between the datasets utilized for external tools and the ReID datasets and the complicated matching process make these methods unreliable and sensitive to noises. In this paper, we propose a Region Generation and Assessment Network (RGANet) to effectively and efficiently detect the human body regions and highlight the important regions. In the proposed RGANet, we first devise a Region Generation Module (RGM) which utilizes the pre-trained CLIP to locate the human body regions using semantic prototypes extracted from text descriptions. Learnable prompt is designed to eliminate domain gap between CLIP datasets and ReID datasets. Then, to measure the importance of each generated region, we introduce a Region Assessment Module (RAM) that assigns confidence scores to different regions and reduces the negative impact of the occlusion regions by lower scores. The RAM consists of a discrimination-aware indicator and an invariance-aware indicator, where the former indicates the capability to distinguish from different identities and the latter represents consistency among the images of the same class of human body regions. Extensive experimental results for six widely-used benchmarks including three tasks (occluded, partial, and holistic) demonstrate the superiority of RGANet against state-of-the-art methods.

Text-based Person Search (TBPS) aims to retrieve images of target pedestrian indicated by textual descriptions. It is essential for TBPS to extract fine-grained local features and align them crossing modality. Existing methods utilize external tools or heavy cross-modal interaction to achieve explicit alignment of cross-modal fine-grained features, which is inefficient and time-consuming. In this work, we propose a Vision-Guided Semantic-Group Network (VGSG) for text-based person search to extract well-aligned fine-grained visual and textual features. In the proposed VGSG, we develop a Semantic-Group Textual Learning (SGTL) module and a Vision-guided Knowledge Transfer (VGKT) module to extract textual local features under the guidance of visual local clues. In SGTL, in order to obtain the local textual representation, we group textual features from the channel dimension based on the semantic cues of language expression, which encourages similar semantic patterns to be grouped implicitly without external tools. In VGKT, a vision-guided attention is employed to extract visual-related textual features, which are inherently aligned with visual cues and termed vision-guided textual features. Furthermore, we design a relational knowledge transfer, including a vision-language similarity transfer and a class probability transfer, to adaptively propagate information of the vision-guided textual features to semantic-group textual features. With the help of relational knowledge transfer, VGKT is capable of aligning semantic-group textual features with corresponding visual features without external tools and complex pairwise interaction. Experimental results on two challenging benchmarks demonstrate its superiority over state-of-the-art methods.

We study universal zero-shot segmentation in this work to achieve panoptic, instance, and semantic segmentation for novel categories without any training samples. Such zero-shot segmentation ability relies on inter-class relationships in semantic space to transfer the visual knowledge learned from seen categories to unseen ones. Thus, it is desired to well bridge semantic-visual spaces and apply the semantic relationships to visual feature learning. We introduce a generative model to synthesize features for unseen categories, which links semantic and visual spaces as well as address the issue of lack of unseen training data. Furthermore, to mitigate the domain gap between semantic and visual spaces, firstly, we enhance the vanilla generator with learned primitives, each of which contains fine-grained attributes related to categories, and synthesize unseen features by selectively assembling these primitives. Secondly, we propose to disentangle the visual feature into the semantic-related part and the semantic-unrelated part that contains useful visual classification clues but is less relevant to semantic representation. The inter-class relationships of semantic-related visual features are then required to be aligned with those in semantic space, thereby transferring semantic knowledge to visual feature learning. The proposed approach achieves impressively state-of-the-art performance on zero-shot panoptic segmentation, instance segmentation, and semantic segmentation.

Zero-shot instance segmentation aims to detect and precisely segment objects of unseen categories without any training samples. Since the model is trained on seen categories, there is a strong bias that the model tends to classify all the objects into seen categories. Besides, there is a natural confusion between background and novel objects that have never shown up in training. These two challenges make novel objects hard to be raised in the final instance segmentation results. It is desired to rescue novel objects from background and dominated seen categories. To this end, we propose D2Zero with Semantic-Promoted Debiasing and Background Disambiguation to enhance the performance of Zero-shot instance segmentation. Semantic-promoted debiasing utilizes inter-class semantic relationships to involve unseen categories in visual feature training and learns an input-conditional classifier to conduct dynamical classification based on the input image. Background disambiguation produces image-adaptive background representation to avoid mistaking novel objects for background. Extensive experiments show that we significantly outperform previous state-of-the-art methods by a large margin, e.g., 16.86% improvement on COCO.

This paper strives for motion expressions guided video segmentation, which focuses on segmenting objects in video content based on a sentence describing the motion of the objects. Existing referring video object datasets typically focus on salient objects and use language expressions that contain excessive static attributes that could potentially enable the target object to be identified in a single frame. These datasets downplay the importance of motion in video content for language-guided video object segmentation. To investigate the feasibility of using motion expressions to ground and segment objects in videos, we propose a large-scale dataset called MeViS, which contains numerous motion expressions to indicate target objects in complex environments. We benchmarked 5 existing referring video object segmentation (RVOS) methods and conducted a comprehensive comparison on the MeViS dataset. The results show that current RVOS methods cannot effectively address motion expression-guided video segmentation. We further analyze the challenges and propose a baseline approach for the proposed MeViS dataset. The goal of our benchmark is to provide a platform that enables the development of effective language-guided video segmentation algorithms that leverage motion expressions as a primary cue for object segmentation in complex video scenes. The proposed MeViS dataset has been released at https://henghuiding.github.io/MeViS.

Video object segmentation (VOS) aims at segmenting a particular object throughout the entire video clip sequence. The state-of-the-art VOS methods have achieved excellent performance (e.g., 90+% $\mathcal{J}$ & $\mathcal{F}$) on existing datasets. However, since the target objects in these existing datasets are usually relatively salient, dominant, and isolated, VOS under complex scenes has rarely been studied. To revisit VOS and make it more applicable in the real world, we collect a new VOS dataset called coMplex video Object SEgmentation (MOSE) to study the tracking and segmenting objects in complex scenarios. MOSE contains 2,149 video clips and 5,200 objects from 36 categories, with 431,725 high-quality object segmentation masks. The most notable feature of MOSE dataset is complex scenes with crowded and occluded objects. The target objects in the videos are commonly occluded by others and disappear in some frames. To analyze the proposed MOSE dataset, we benchmark 18 existing VOS methods under 4 different settings on the proposed MOSE dataset and conduct comprehensive comparisons. The experiments show that current VOS algorithms cannot well perceive objects in complex scenes. For example, under the semi-supervised VOS setting, the highest $\mathcal{J}$ & $\mathcal{F}$ by existing state-of-the-art VOS methods is only 59.4% on MOSE, much lower than their ∼90% $\mathcal{J}$ & $\mathcal{F}$ performance on DAVIS. The results reveal that although excellent performance has been achieved on existing benchmarks, there are unresolved challenges under complex scenes and more efforts are desired to explore these challenges in the future.

In this work, we address the challenging task of few-shot and zero-shot 3D point cloud semantic segmentation. The success of few-shot semantic segmentation in 2D computer vision is mainly driven by the pre-training on large-scale datasets like imagenet. The feature extractor pre-trained on large-scale 2D datasets greatly helps the 2D few-shot learning. However, the development of 3D deep learning is hindered by the limited volume and instance modality of datasets due to the significant cost of 3D data collection and annotation. This results in less representative features and large intra-class feature variation for few-shot 3D point cloud segmentation. As a consequence, directly extending existing popular prototypical methods of 2D few-shot classification/segmentation into 3D point cloud segmentation won't work as well as in 2D domain. To address this issue, we propose a Query-Guided Prototype Adaption (QGPA) module to adapt the prototype from support point clouds feature space to query point clouds feature space. With such prototype adaption, we greatly alleviate the issue of large feature intra-class variation in point cloud and significantly improve the performance of few-shot 3D segmentation. Besides, to enhance the representation of prototypes, we introduce a Self-Reconstruction (SR) module that enables prototype to reconstruct the support mask as well as possible. Moreover, we further consider zero-shot 3D point cloud semantic segmentation where there is no support sample. To this end, we introduce category words as semantic information and propose a semantic-visual projection model to bridge the semantic and visual spaces. Our proposed method surpasses state-of-the-art algorithms by a considerable 7.90% and 14.82% under the 2-way 1-shot setting on S3DIS and ScanNet benchmarks, respectively.

Fully-supervised vehicle re-identification (re-ID) methods are faced with performance degradation when applied to new image domains. Therefore, developing unsupervised domain adaptation (UDA) to transfer the knowledge from learned source domain to new unlabeled target domain becomes an indispensable task. It is challenging because different domains have various image appearances, such as different backgrounds, illuminations and resolutions, especially when cameras have different viewpoints. To tackle this domain gap issue, a novel Transformer-based Domain-Specific Representation learning network (TDSR) is proposed to dynamically focus on corresponding detailed hints for each domain. Specifically, with the source and target domain being trained simultaneously, a domain encoding module is proposed to introduce domain information into the network. The original features of source and target domains are enriched with these domain encodings first, and then sequentially processed by a Transformer encoder to model contextual information and a decoder to summarize the encoded features into the final domain-specific feature representations. Moreover, we propose a Contrastive Clustering Loss (CCL) to directly optimize the distribution of features at cluster level. Instances are overall pulled closer to the prototype of the same identity, and pushed farther from the prototypes of different identities. It helps compact the clusters in the latent space and improve the discriminative capability of the network, leading to more accurate pseudo-label assignment in TDSR. Our method outperforms the state-of-the-art UDA methods on vehicle re-ID benchmark datasets VeRi and VehicleID on both real-world to real-world and synthetic to real-world settings.

Extracting robust feature representation is one of the key challenges in object re-identification (ReID). Although convolution neural network (CNN)-based methods have achieved great success, they only process one local neighborhood at a time and suffer from information loss on details caused by convolution and downsampling operators (e.g. pooling and strided convolution). To overcome these limitations, we propose a pure transformer-based object ReID framework named TransReID. Specifically, we first encode an image as a sequence of patches and build a transformer-based strong baseline with a few critical improvements, which achieves competitive results on several ReID benchmarks with CNN-based methods. To further enhance the robust feature learning in the context of transformers, two novel modules are carefully designed. (i) The jigsaw patch module (JPM) is proposed to rearrange the patch embeddings via shift and patch shuffle operations which generates robust features with improved discrimination ability and more diversified coverage. (ii) The side information embeddings (SIE) is introduced to mitigate feature bias towards camera/view variations by plugging in learnable embeddings to incorporate these non-visual clues. To the best of our knowledge, this is the first work to adopt a pure transformer for ReID research. Experimental results of TransReID are superior promising, which achieve state-of-the-art performance on both person and vehicle ReID benchmarks. Code is available at https://github.com/heshuting555/TransReID.