论文检索

Xin Tong, Shi Peng, Baojie Tian, Yufei Guo, Xuhui Huang, Zhe Ma

Classical Transformer-based line segment detection methods have delivered impressive results. However, we observe that some accurately detected line segments are assigned low confidence scores during prediction, causing them to be ranked lower and potentially suppressed. Additionally, these models often require prolonged training periods to achieve strong performance, largely due to the necessity of bipartite matching. In this paper, we introduce RANK-LETR, a novel Transformer-based line segment detection method. Our approach leverages learnable geometric information to refine the ranking of predicted line segments by enhancing the confidence scores of high-quality predictions in a posterior verification step. We also propose a new line segment proposal method, wherein the feature point nearest to the centroid of the line segment directly predicts the location, significantly improving training efficiency and stability. Moreover, we introduce a line segment ranking loss to stabilize rankings during training, thereby enhancing the generalization capability of the model. Experimental results demonstrate that our method outperforms other Transformer-based and CNN-based approaches in prediction accuracy while requiring fewer training epochs than previous Transformer-based models.

Tony Cheng Tong, Sirui He, Zhiwen Shao, Dit-Yan Yeung

Evaluation metric of visual captioning is important yet not thoroughly explored. Traditional metrics like BLEU, METEOR, CIDEr, and ROUGE often miss semantic depth, while trained metrics such as CLIP-Score, PAC-S, and Polos are limited in zero-shot scenarios. Advanced Language Model-based metrics also struggle with aligning to nuanced human preferences. To address these issues, we introduce G-VEval, a novel metric inspired by G-Eval and powered by the new GPT-4o. G-VEval uses chain-of-thought reasoning in large multimodal models and supports three modes: reference-free, reference-only, and combined, accommodating both video and image inputs. We also propose MSVD-Eval, a new dataset for video captioning evaluation, to establish a more transparent and consistent framework for both human experts and evaluation metrics. It is designed to address the lack of clear criteria in existing datasets by introducing distinct dimensions of Accuracy, Completeness, Conciseness, and Relevance (ACCR). Extensive results show that G-VEval outperforms existing methods in correlation with human annotations, as measured by Kendall tau-b and Kendall tau-c. This provides a flexible solution for diverse captioning tasks and suggests a straightforward yet effective approach for large language models to understand video content, paving the way for advancements in automated captioning.

Xie Tianyidan, Rui Ma, Qian Wang, Xiaoqian Ye, Feixuan Liu, Ying Tai, Zhenyu Zhang, Lanjun Wang, Zili Yi

Recent advancements in image-conditioned image generation have demonstrated substantial progress. However, foreground-conditioned image generation remains underexplored, encountering challenges such as compromised object integrity, foreground-background inconsistencies, limited diversity, and reduced control flexibility. These challenges arise from current end-to-end inpainting models, which suffer from inaccurate training masks, limited foreground semantic understanding, data distribution biases, and inherent interference between visual and textual prompts. To overcome these limitations, we present Anywhere, a multi-agent framework that departs from the traditional end-to-end approach. In this framework, each agent is specialized in a distinct aspect, such as foreground understanding, diversity enhancement, object integrity protection, and textual prompt consistency. Our framework is further enhanced with the ability to incorporate optional user textual inputs, perform automated quality assessments, and initiate re-generation as needed. Comprehensive experiments demonstrate that this modular design effectively overcomes the limitations of existing end-to-end models, resulting in higher fidelity, quality, diversity and controllability in foreground-conditioned image generation. Additionally, the Anywhere framework is extensible, allowing it to benefit from future advancements in each individual agent.

Yunjie Tian, Tianren Ma, Lingxi Xie, Qixiang Ye

In this study, we establish a benchmark and a baseline approach for Multimodal referring and grounding with Chain-of-Questions (MCQ), opening up a promising direction for ‘logical’ multimodal dialogues. The newly collected dataset, named CB-300K, spans challenges including probing dialogues with spatial relationship among multiple objects, consistent reasoning, and complex question chains. The baseline approach, termed ChatterBox, involves a modularized design and a referent feedback mechanism to ensure logical coherence in continuous referring and grounding tasks. This design reduces the risk of referential confusion, simplifies the training process, and presents validity in retaining the language model’s generation ability. Experiments show that ChatterBox demonstrates superiority in MCQ both quantitatively and qualitatively, paving a new path towards multimodal dialogue scenarios with logical interactions.

Yu Tian, Yixuan Li, Baoliang Chen, Hanwei Zhu, Shiqi Wang, Sam Kwong

Assessing the quality of artificial intelligence-generated images (AIGIs) plays a crucial role in their application in real-world scenarios. However, traditional image quality assessment (IQA) algorithms primarily focus on low-level visual perception, while existing IQA works on AIGIs overemphasize the generated content itself, neglecting its effectiveness in real-world applications. To bridge this gap, we propose AIGI-VC, a quality assessment database for AI-Generated Images in Visual Communication, which studies the communicability of AIGIs in the advertising field from the perspectives of information clarity and emotional interaction. The dataset consists of 2,500 images spanning 14 advertisement topics and 8 emotion types. It provides coarse-grained human preference annotations and fine-grained preference descriptions, benchmarking the abilities of IQA methods in preference prediction, interpretation, and reasoning. We conduct an empirical study of existing representative IQA methods and large multi-modal models on the AIGI-VC dataset, uncovering their strengths and weaknesses.

Xuanyu Tian, Lixuan Chen, Qing Wu, Chenhe Du, Jingjing Shi, Hongjiang Wei, Yuyao Zhang

Emerging unsupervised implicit neural representation (INR) methods, such as NeRP, NeAT, and SCOPE, have shown great potential in addressing sparse-view computed tomography (SVCT) inverse problems. While these INR-based methods perform well on relatively dense SVCT reconstructions, they struggle to achieve comparable performance with supervised methods in sparser SVCT scenarios and are prone to being affected by noise, limiting their applicability in real clinical settings. Additionally, current methods have not fully explored the use of image domain priors for solving SVCT inverse problems. In this work, we demonstrate that imperfect reconstruction results can provide effective image domain priors for INRs to enhance performance. To leverage this, we introduce Self-prior embedding neural representation (Spener), a novel unsupervised method for SVCT reconstruction that integrates iterative reconstruction algorithms. During each iteration, Spener extracts local image prior features from the previous iteration and embeds them to constrain the solution space. Experimental results on multiple CT datasets show that our unsupervised Spener method achieves performance comparable to supervised state-of-the-art (SOTA) methods on in-domain data while outperforming them on out-of-domain datasets. Moreover, Spener significantly improves the performance of INR-based methods in handling SVCT with noisy sinograms.

Qijian Tian, Xin Tan, Yuan Xie, Lizhuang Ma

We propose DrivingForward, a feed-forward Gaussian Splatting model that reconstructs driving scenes from flexible surround-view input. Driving scene images from vehicle-mounted cameras are typically sparse, with limited overlap, and the movement of the vehicle further complicates the acquisition of camera extrinsics. To tackle these challenges and achieve real-time reconstruction, we jointly train a pose network, a depth network, and a Gaussian network to predict the Gaussian primitives that represent the driving scenes. The pose network and depth network determine the position of the Gaussian primitives in a self-supervised manner, without using depth ground truth and camera extrinsics during training. The Gaussian network independently predicts primitive parameters from each input image, including covariance, opacity, and spherical harmonics coefficients. At the inference stage, our model can achieve feed-forward reconstruction from flexible multi-frame surround-view input. Experiments on the nuScenes dataset show that our model outperforms existing state-of-the-art feed-forward and scene-optimized reconstruction methods in terms of reconstruction.

Haitao Tian, Pierre Payeur

Existing skeleton-based human action classification models rely on well-trimmed action-specific skeleton videos for both training and testing, precluding their scalability to real-world applications where untrimmed videos exhibiting concatenated actions are predominant. To overcome this limitation, recently introduced skeleton action segmentation models involve un-trimmed skeleton videos into end-to-end training. The model is optimized to provide frame-wise predictions for any length of testing videos, simultaneously realizing action localization and classification. Yet, achieving such an improvement im-poses frame-wise annotated skeleton videos, which remains time-consuming in practice. This paper features a novel framework for skeleton-based action segmentation trained on short trimmed skeleton videos, but that can run on longer un-trimmed videos. The approach is implemented in three steps: Stitch, Contrast, and Segment. First, Stitch proposes a tem-poral skeleton stitching scheme that treats trimmed skeleton videos as elementary human motions that compose a semantic space and can be sampled to generate multi-action stitched se-quences. Contrast learns contrastive representations from stitched sequences with a novel discrimination pretext task that enables a skeleton encoder to learn meaningful action-temporal contexts to improve action segmentation. Finally, Segment relates the proposed method to action segmentation by learning a segmentation layer while handling particular da-ta availability. Experiments involve a trimmed source dataset and an untrimmed target dataset in an adaptation formulation for real-world skeleton-based human action segmentation to evaluate the effectiveness of the proposed method.

Xiao Teng, Long Lan, Dingyao Chen, Kele Xu, Nan Yin

Unsupervised visible-infrared person re-identification (USL-VI-ReID) is of great research and practical significance yet remains challenging due to the absence of annotations. Existing approaches aim to learn modality-invariant representations in an unsupervised setting. However, these methods often encounter label noise within and across modalities due to suboptimal clustering results and considerable modality discrepancies, which impedes effective training. To address these challenges, we propose a straightforward yet effective solution for USL-VI-ReID by mitigating universal label noise using neighbor information. Specifically, we introduce the Neighbor-guided Universal Label Calibration (N-ULC) module, which replaces explicit hard pseudo labels in both homogeneous and heterogeneous spaces with soft labels derived from neighboring samples to reduce label noise. Additionally, we present the Neighbor-guided Dynamic Weighting (N-DW) module to enhance training stability by minimizing the influence of unreliable samples. Extensive experiments on the RegDB and SYSU-MM01 datasets demonstrate that our method outperforms existing USL-VI-ReID approaches, despite its simplicity.

Fenfang Tao, Guo-Sen Xie, Fang Zhao, Xiangbo Shu

Few-shot anomaly detection (FSAD) aims to detect unseen anomaly regions with the guidance of very few normal support images from the same class. Existing FSAD methods usually find anomalies by directly designing complex text prompts to align them with visual features under the prevailing large vision-language model paradigm. However, these methods, almost always, neglect intrinsic contextual information in visual features, e.g., the interaction relationships between different vision layers, which is an important clue for detecting anomalies comprehensively. To this end, we propose a kernel-aware graph prompt learning framework, termed as KAG-prompt, by reasoning the cross-layer relations among visual features for FSAD. Specifically, a kernel-aware hierarchical graph is built by taking the different layer features focusing on anomalous regions of different sizes as nodes, meanwhile, the relationships between arbitrary pairs of nodes stand for the edges of the graph. By message passing over this graph, KAG-prompt can capture cross-layer contextual information, thus leading to more accurate anomaly prediction. Moreover, to integrate the information of multiple important anomaly signals in the prediction map, we propose a novel image-level scoring method based on multi-level information fusion. Extensive experiments on MVTecAD and VisA datasets show that KAG-prompt achieves state-of-the-art FSAD results for image-level/pixel-level anomaly detection.

Zichen Tang, Hongyu Yang, Hanchen Zhang, Jiaxin Chen, Di Huang

Advancements in neural implicit representations and differentiable rendering have markedly improved the ability to learn animatable 3D avatars from sparse multi-view RGB videos. However, current methods that map observation space to canonical space often face challenges in capturing pose-dependent details and generalizing to novel poses. While diffusion models have demonstrated remarkable zero-shot capabilities in 2D image generation, their potential for creating animatable 3D avatars from 2D inputs remains underexplored. In this work, we introduce 3D²-Actor, a novel approach featuring a pose-conditioned 3D-aware human modeling pipeline that integrates iterative 2D denoising and 3D rectifying steps. The 2D denoiser, guided by pose cues, generates detailed multi-view images that provide the rich feature set necessary for high-fidelity 3D reconstruction and pose rendering. Complementing this, our Gaussian-based 3D rectifier renders images with enhanced 3D consistency through a two-stage projection strategy and a novel local coordinate representation. Additionally, we propose an innovative sampling strategy to ensure smooth temporal continuity across frames in video synthesis. Our method effectively addresses the limitations of traditional numerical solutions in handling ill-posed mappings, producing realistic and animatable 3D human avatars. Experimental results demonstrate that 3D²-Actor excels in high-fidelity avatar modeling and robustly generalizes to novel poses.

Zhihao Tang, Xi Zhang, Chaozhuo Li

Deep learning has significantly enhanced survival prediction using whole slide images (WSIs) by adopting a two-stage learning paradigm: WSI preparation and patient-level prediction. While existing research generally concentrates on developing advanced patient-level prediction modules, the critical importance of WSI preparation has been largely overlooked. In practice, WSI preparation is influenced by numerous factors, including tissue heterogeneity, sampling strategies, and technical considerations. These uncontrollable external factors incur variability in the number of WSIs among patients, introducing significant bias and resulting in inferior performance for patients with few WSIs. To address this challenge, we propose a novel approach named WSI-Diffusion. Unlike existing WSI generation models that produce augmented versions of input WSIs, our method generates entirely new WSIs in representation space to serve as complementary data. WSIDiffusion employs a two-stage hierarchical diffusion process. Two novel modules, WSI-level and patch-level Diffusers are designed to capture complex correlations between WSIs and patches. The generated WSIs are integrated as supplementary data, and a light patient-level prediction module is then trained for survival prediction. Experimental results across five datasets demonstrate the superiority of our proposal.

Zhenyu Tang, Junwu Zhang, Xinhua Cheng, Wangbo Yu, Chaoran Feng, Yatian Pang, Bin Lin, Li Yuan

Recent 3D large reconstruction models typically employ a two-stage process, including first generate multi-view images by a multi-view diffusion model, and then utilize a feed-forward model to reconstruct images to 3D content. However, multi-view diffusion models often produce low-quality and inconsistent images, adversely affecting the quality of the final 3D reconstruction. To address this issue, we propose a unified 3D generation framework called Cycle3D, which cyclically utilizes a 2D diffusion-based generation module and a feed-forward 3D reconstruction module during the multi-step diffusion process. Concretely, 2D diffusion model is applied for generating high-quality texture, and the reconstruction model guarantees multi-view consistency. Moreover, 2D diffusion model can further control the generated content and inject reference-view information for unseen views, thereby enhancing the diversity and texture consistency of 3D generation during the denoising process. Extensive experiments demonstrate the superior ability of our method to create 3D content with high-quality and consistency compared with state-of-the-art baselines.

Zhenhua Tang, Bin Zhu, Yanbin Hao, Chong-Wah Ngo, Richang Hong

Intent-based grasp generation inherently involves challenges such as manipulation ambiguity and modality gaps. To address these, we propose a novel Retrieval-Augmented Grasp Generation model (RAGG). Our key insight is that when humans manipulate new objects, they initially mimic the interaction patterns observed in similar objects, then progressively adjust hand-object contact. Consequently, we develop RAGG as a two-stage approach, encompassing retrieval-guided generation and structurally stable grasp refinement. In the first stage, we propose a Retrieval-Augmented Diffusion Model (ReDim), which identifies the most relevant interaction instance from a knowledge base to explicitly guide grasp generation, thereby mitigating ambiguity and bridging modality gaps to ensure semantically correct manipulation. In the second stage, we introduce a Progressive Refinement Network (PRN) with Kolmogorov-Arnold Network (KAN) layers to refine the generated coarse grasp, employing a Structural Similarity Index loss to constrain the spatial relationship between the hand and the object, thus ensuring the stability of the grasp. Extensive experiments on the OakInk and GRAB benchmarks demonstrate that RAGG achieves superior results compared to state-of-the-art approach, indicating not only better physical feasibility and controllability but also strong generalization and interpretability for unseen objects.

Yunlong Tang, Gen Zhan, Li Yang, Yiting Liao, Chenliang Xu

Video saliency prediction aims to identify the regions in a video that attract human attention and gaze, driven by bottom-up features from the video and top-down processes like memory and cognition. Among these top-down influences, language plays a crucial role in guiding attention by shaping how visual information is interpreted. Existing methods primarily focus on modeling perceptual information while neglecting the reasoning process facilitated by language, where ranking cues are crucial outcomes of this process and practical guidance for saliency prediction. In this paper, we propose CaRDiff (Caption, Rank, and generate with Diffusion), a framework that imitates the process by integrating multimodal large language model (MLLM), a grounding module, and a diffusion model, to enhance video saliency prediction. Specifically, we introduce a novel prompting method VSOR-CoT (Video Slient Object Ranking Chain of Thought), which utilizes an MLLM with a grounding module to caption video content and infer salient objects along with their rankings and positions. This process derives ranking maps that can be sufficiently leveraged by the diffusion model to accurately decode the saliency maps for the given video. Extensive experiments showcase the effectiveness of VSOR-CoT in improving the performance of video saliency prediction. The proposed CaRDiff performs better than state-of-the-art models on the MVS dataset and demonstrates cross-dataset capabilities on the DHF1k dataset through zero-shot evaluation.

Yunlong Tang, Daiki Shimada, Jing Bi, Mingqian Feng, Hang Hua, Chenliang Xu

Large language models (LLMs) have demonstrated remarkable capabilities in natural language and multimodal domains. By fine-tuning multimodal LLMs with temporal annotations from well-annotated datasets, e.g., dense video captioning datasets, their temporal understanding capacity in video-language tasks can be obtained. However, there is a notable lack of untrimmed audio-visual video datasets with precise temporal annotations for events. This deficiency hinders LLMs from learning the alignment between time, audio-visual events, and text tokens, thus impairing their ability to localize audio-visual events in videos temporally. To address this gap, we introduce PU-VALOR, a comprehensive audio-visual dataset comprising over 114,081 pseudo-untrimmed videos with detailed temporal annotations. PU-VALOR is derived from the large-scale but coarse-annotated audio-visual dataset VALOR, through a subtle method involving event-based video clustering, random temporal scaling, and permutation. By fine-tuning a multimodal LLM on PU-VALOR, we developed AVicuna, a model capable of aligning audio-visual events with temporal intervals and corresponding text tokens. AVicuna excels in temporal localization and time-aware dialogue capabilities. Our experiments demonstrate that AVicuna effectively handles temporal understanding in audio-visual videos and achieves state-of-the-art performance on open-ended video QA, audio-visual QA, and audio-visual event dense localization tasks.

Yuan Tang, Xu Han, Xianzhi Li, Qiao Yu, Jinfeng Xu, Yixue Hao, Long Hu, Min Chen

Enabling Large Language Models (LLMs) to comprehend the 3D physical world remains a significant challenge. Due to the lack of large-scale 3D-text pair datasets, the success of LLMs has yet to be replicated in 3D understanding. In this paper, we rethink this issue and propose a new task: 3D Data-Efficient Point-Language Understanding. The goal is to enable LLMs to achieve robust 3D object understanding with minimal 3D point cloud and text data pairs. To address this task, we introduce GreenPLM, which leverages more text data to compensate for the lack of 3D data. First, inspired by using CLIP to align images and text, we utilize a pre-trained point cloud-text encoder to map the 3D point cloud space to the text space. This mapping leaves us to seamlessly connect the text space with LLMs. Once the point-text-LLM connection is established, we further enhance text-LLM alignment by expanding the intermediate text space, thereby reducing the reliance on 3D point cloud data. Specifically, we generate 6M free-text descriptions of 3D objects, and design a three-stage training strategy to help LLMs better explore the intrinsic connections between different modalities. To achieve efficient modality alignment, we design a zero-parameter cross-attention module for token pooling. Extensive experimental results show that GreenPLM requires only 12% of the 3D training data used by existing state-of-the-art models to achieve superior 3D understanding. Remarkably, GreenPLM also achieves competitive performance using text-only data.

Tao Tang, Dafeng Wei, Zhengyu Jia, Tian Gao, Changwei Cai, Chengkai Hou, Peng Jia, Kun Zhan, Haiyang Sun, Fan JingChen 等

The rapid development of the autonomous driving industry has led to a significant accumulation of autonomous driving data. Consequently, there comes a growing demand for retrieving data to provide specialized optimization. However, directly applying previous image retrieval methods faces several challenges, such as the lack of global feature representation and inadequate text retrieval ability for complex driving scenes. To address these issues, firstly, we propose the BEV-TSR framework which leverages descriptive text as an input to retrieve corresponding scenes in the Bird’s Eye View (BEV) space. Then to facilitate complex scene retrieval with extensive text descriptions, we employ a large language model (LLM) to extract the semantic features of the text inputs and incorporate knowledge graph embeddings to enhance the semantic richness of the language embedding. To achieve feature alignment between the BEV feature and language embedding, we propose Shared Cross-modal Embedding with a set of shared learnable embeddings to bridge the gap between these two modalities, and employ a caption generation task to further enhance the alignment. Furthermore, there lack of well-formed retrieval datasets for effective evaluation. To this end, we establish a multi-level retrieval dataset, nuScenes-Retrieval, based on the widely adopted nuScenes dataset. Experimental results on the multi-level nuScenes-Retrieval show that BEV-TSR achieves state-of-the-art performance, e.g., 85.78% and 87.66% top-1 accuracy on scene-to-test and text-to-scene retrieval respectively.

Shengeng Tang, Jiayi He, Dan Guo, Yanyan Wei, Feng Li, Richang Hong

Sign Language Production (SLP) aims to generate semantically consistent sign videos from textual statements, where the conversion from textual glosses to sign poses (G2P) is a crucial step. Existing G2P methods typically treat sign poses as discrete three-dimensional coordinates and directly fit them, which overlooks the relative positional relationships among joints. To this end, we provide a new perspective, constraining joint associations and gesture details by modeling the limb bones to improve the accuracy and naturalness of the generated poses. In this work, we propose a pioneering iconicity disentangled diffusion framework, termed Sign-IDD, specifically designed for SLP. Sign-IDD incorporates a novel Iconicity Disentanglement (ID) module to bridge the gap between relative positions among joints. The ID module disentangles the conventional 3D joint representation into a 4D bone representation, comprising the 3D spatial direction vector and 1D spatial distance vector between adjacent joints. Additionally, an Attribute Controllable Diffusion (ACD) module is introduced to further constrain joint associations, in which the attribute separation layer aims to separate the bone direction and length attributes, and the attribute control layer is designed to guide the pose generation by leveraging the above attributes. The ACD module utilizes the gloss embeddings as semantic conditions and finally generates sign poses from noise embeddings. Extensive experiments on PHOENIX14T and USTC-CSL datasets validate the effectiveness of our method.

Luyang Tang, Jiayu Yang, Rui Peng, Yongqi Zhai, Shihe Shen, Ronggang Wang

The success of 3D Gaussian Splatting (3DGS) in static scenes has inspired numerous attempts to construct Free-Viewpoint Videos (FVVs) of dynamic scenes from multi-view videos. Despite advancements in current techniques, simultaneously achieving photo-realistic view synthesis results, fast on-the-fly training, real-time rendering, and low storage costs remains a formidable problem. To address these challenges, we propose the first Gaussian-based streamable FVV intelligent compression framework named iFVC. Specifically, we utilize an anchor-based Gaussian representation to model the scene. To achieve on-the-fly training, we propose a Binary Transformation Cache (BTC) to model the dynamic changes between adjacent timesteps, which not only ensures compactness but also supports precise bit rate estimation. Furthermore, we carefully design a high-resolution transformation tri-plane assisted by a saliency grid as our BTC, allowing for accurate dynamic capture. The entire pipeline is regarded as a joint optimization of rate and distortion to achieve optimal compression performance. Experiments on widely used datasets demonstrate the state-of-the-art performance of our framework in both synthesis quality and efficiency, i.e., achieving per-frame training in 13 seconds with a storage cost of 0.1 MB and real-time rendering at 120 FPS.