Heng Wang

Cheng-En Wu, Yu Tian, Haichao Yu et al.

Vision-language models such as CLIP learn a generic text-image embedding from large-scale training data. A vision-language model can be adapted to a new classification task through few-shot prompt tuning. We find that such a prompt tuning process is highly robust to label noises. This intrigues us to study the key reasons contributing to the robustness of the prompt tuning paradigm. We conducted extensive experiments to explore this property and find the key factors are: 1) the fixed classname tokens provide a strong regularization to the optimization of the model, reducing gradients induced by the noisy samples; 2) the powerful pre-trained image-text embedding that is learned from diverse and generic web data provides strong prior knowledge for image classification. Further, we demonstrate that noisy zero-shot predictions from CLIP can be used to tune its own prompt, significantly enhancing prediction accuracy in the unsupervised setting. The code is available at https://github.com/CEWu/PTNL.

Runkai Zhao, Heng Wang, Chaoyi Zhang et al.

Digital neuron reconstruction from 3D microscopy images is an essential technique for investigating brain connectomics and neuron morphology. Existing reconstruction frameworks use convolution-based segmentation networks to partition the neuron from noisy backgrounds before applying the tracing algorithm. The tracing results are sensitive to the raw image quality and segmentation accuracy. In this paper, we propose a novel framework for 3D neuron reconstruction. Our key idea is to use the geometric representation power of the point cloud to better explore the intrinsic structural information of neurons. Our proposed framework adopts one graph convolutional network to predict the neural skeleton points and another one to produce the connectivity of these points. We finally generate the target SWC file through the interpretation of the predicted point coordinates, radius, and connections. Evaluated on the Janelia-Fly dataset from the BigNeuron project, we show that our framework achieves competitive neuron reconstruction performance. Our geometry and topology learning of point clouds could further benefit 3D medical image analysis, such as cardiac surface reconstruction. Our code is available at https://github.com/RunkaiZhao/PointNeuron.

Zhiyuan Li, Dongnan Liu, Heng Wang et al.

Recently, training an image captioner without annotated image-sentence pairs has gained traction. Previous methods have faced limitations due to either using mismatched corpora for inaccurate pseudo annotations or relying on resource-intensive pre-training. To alleviate these challenges, we propose a new strategy where the prior knowledge from large pre-trained models (LPMs) is distilled and leveraged as supervision, and a retrieval process is integrated to further reinforce its effectiveness. Specifically, we introduce Retrieval-augmented Pseudo Sentence Generation (RaPSG), which can efficiently retrieve highly relevant short region descriptions from the mismatching corpora and use them to generate a variety of high-quality pseudo sentences via LPMs. Additionally, we introduce a fluency filter and a CLIP guidance objective to enhance contrastive information learning. Experimental results indicate that our method outperforms SOTA captioning models across various settings including zero-shot, unsupervised, semi-supervised, and cross-domain scenarios. Code is available at: https://github.com/Zhiyuan-Li-John/RaPSG.

Fan Ma, Xiaojie Jin, Heng Wang et al.

Video-Language Pre-training models have recently significantly improved various multi-modal downstream tasks. Previous dominant works mainly adopt contrastive learning to achieve global feature alignment across modalities. However, the local associations between videos and texts are not modeled, restricting the pre-training models' generality, especially for tasks requiring the temporal video boundary for certain query texts. This work introduces a novel text-video localization pre-text task to enable fine-grained temporal and semantic alignment such that the trained model can accurately perceive temporal boundaries in videos given the text description. Specifically, text-video localization consists of moment retrieval, which predicts start and end boundaries in videos given the text description, and text localization which matches the subset of texts with the video features. To produce temporal boundaries, frame features in several videos are manually merged into a long video sequence that interacts with a text sequence. With the localization task, our method connects the fine-grained frame representations with the word representations and implicitly distinguishes representations of different instances in the single modality. Notably, comprehensive experimental results show that our method significantly improves the state-of-the-art performance on various benchmarks, covering text-to-video retrieval, video question answering, video captioning, temporal action localization and temporal moment retrieval. The code will be released soon.

Heng Wang, Jianbo Ma, Santiago Pascual et al.

Building artificial intelligence (AI) systems on top of a set of foundation models (FMs) is becoming a new paradigm in AI research. Their representative and generative abilities learnt from vast amounts of data can be easily adapted and transferred to a wide range of downstream tasks without extra training from scratch. However, leveraging FMs in cross-modal generation remains under-researched when audio modality is involved. On the other hand, automatically generating semantically-relevant sound from visual input is an important problem in cross-modal generation studies. To solve this vision-to-audio (V2A) generation problem, existing methods tend to design and build complex systems from scratch using modestly sized datasets. In this paper, we propose a lightweight solution to this problem by leveraging foundation models, specifically CLIP, CLAP, and AudioLDM. We first investigate the domain gap between the latent space of the visual CLIP and the auditory CLAP models. Then we propose a simple yet effective mapper mechanism (V2A-Mapper) to bridge the domain gap by translating the visual input between CLIP and CLAP spaces. Conditioned on the translated CLAP embedding, pretrained audio generative FM AudioLDM is adopted to produce high-fidelity and visually-aligned sound. Compared to previous approaches, our method only requires a quick training of the V2A-Mapper. We further analyze and conduct extensive experiments on the choice of the V2A-Mapper and show that a generative mapper is better at fidelity and variability (FD) while a regression mapper is slightly better at relevance (CS). Both objective and subjective evaluation on two V2A datasets demonstrate the superiority of our proposed method compared to current state-of-the-art approaches - trained with 86% fewer parameters but achieving 53% and 19% improvement in FD and CS, respectively.

Heng Wang, Chaoyi Zhang, Jianhui Yu et al.

Dense captioning in 3D point clouds is an emerging vision-and-language task involving object-level 3D scene understanding. Apart from coarse semantic class prediction and bounding box regression as in traditional 3D object detection, 3D dense captioning aims at producing a further and finer instance-level label of natural language description on visual appearance and spatial relations for each scene object of interest. To detect and describe objects in a scene, following the spirit of neural machine translation, we propose a transformer-based encoder-decoder architecture, namely SpaCap3D, to transform objects into descriptions, where we especially investigate the relative spatiality of objects in 3D scenes and design a spatiality-guided encoder via a token-to-token spatial relation learning objective and an object-centric decoder for precise and spatiality-enhanced object caption generation. Evaluated on two benchmark datasets, ScanRefer and ReferIt3D, our proposed SpaCap3D outperforms the baseline method Scan2Cap by 4.94% and 9.61% in CIDEr@0.5IoU, respectively. Our project page with source code and supplementary files is available at https://SpaCap3D.github.io/ .

Shuhong Chen, Kevin Zhang, Yichun Shi et al.

We propose PAniC-3D, a system to reconstruct stylized 3D character heads directly from illustrated (p)ortraits of (ani)me (c)haracters. Our anime-style domain poses unique challenges to single-view reconstruction; compared to natural images of human heads, character portrait illustrations have hair and accessories with more complex and diverse geometry, and are shaded with non-photorealistic contour lines. In addition, there is a lack of both 3D model and portrait illustration data suitable to train and evaluate this ambiguous stylized reconstruction task. Facing these challenges, our proposed PAniC-3D architecture crosses the illustration-to-3D domain gap with a line-filling model, and represents sophisticated geometries with a volumetric radiance field. We train our system with two large new datasets (11.2k Vroid 3D models, 1k Vtuber portrait illustrations), and evaluate on a novel AnimeRecon benchmark of illustration-to-3D pairs. PAniC-3D significantly outperforms baseline methods, and provides data to establish the task of stylized reconstruction from portrait illustrations.

Xinlu Zhang, Yujie Lu, Weizhi Wang et al.

Automatically evaluating vision-language tasks is challenging, especially when it comes to reflecting human judgments due to limitations in accounting for fine-grained details. Although GPT-4V has shown promising results in various multi-modal tasks, leveraging GPT-4V as a generalist evaluator for these tasks has not yet been systematically explored. We comprehensively validate GPT-4V's capabilities for evaluation purposes, addressing tasks ranging from foundational image-to-text and text-to-image synthesis to high-level image-to-image translations and multi-images to text alignment. We employ two evaluation methods, single-answer grading and pairwise comparison, using GPT-4V. Notably, GPT-4V shows promising agreement with humans across various tasks and evaluation methods, demonstrating immense potential for multi-modal LLMs as evaluators. Despite limitations like restricted visual clarity grading and real-world complex reasoning, its ability to provide human-aligned scores enriched with detailed explanations is promising for universal automatic evaluator.

Shunqi Mao, Chaoyi Zhang, Heng Wang et al.

In audio-visual navigation (AVN), an intelligent agent needs to navigate to a constantly sound-making object in complex 3D environments based on its audio and visual perceptions. While existing methods attempt to improve the navigation performance with preciously designed path planning or intricate task settings, none has improved the model generalisation on unheard sounds with task settings unchanged. We thus propose a contrastive learning-based method to tackle this challenge by regularising the audio encoder, where the sound-agnostic goal-driven latent representations can be learnt from various audio signals of different classes. In addition, we consider two data augmentation strategies to enrich the training sounds. We demonstrate that our designs can be easily equipped to existing AVN frameworks to obtain an immediate performance gain (13.4%$\uparrow$ in SPL on Replica and 12.2%$\uparrow$ in SPL on MP3D). Our project is available at https://AV-GeN.github.io/.

Jianglong Ye, Peng Wang, Kejie Li et al.

Zero-shot novel view synthesis (NVS) from a single image is an essential problem in 3D object understanding. While recent approaches that leverage pre-trained generative models can synthesize high-quality novel views from in-the-wild inputs, they still struggle to maintain 3D consistency across different views. In this paper, we present Consistent-1-to-3, which is a generative framework that significantly mitigates this issue. Specifically, we decompose the NVS task into two stages: (i) transforming observed regions to a novel view, and (ii) hallucinating unseen regions. We design a scene representation transformer and view-conditioned diffusion model for performing these two stages respectively. Inside the models, to enforce 3D consistency, we propose to employ epipolor-guided attention to incorporate geometry constraints, and multi-view attention to better aggregate multi-view information. Finally, we design a hierarchy generation paradigm to generate long sequences of consistent views, allowing a full 360-degree observation of the provided object image. Qualitative and quantitative evaluation over multiple datasets demonstrates the effectiveness of the proposed mechanisms against state-of-the-art approaches. Our project page is at https://jianglongye.com/consistent123/

Mude Hui, Siwei Yang, Bingchen Zhao et al.

This study introduces HQ-Edit, a high-quality instruction-based image editing dataset with around 200,000 edits. Unlike prior approaches relying on attribute guidance or human feedback on building datasets, we devise a scalable data collection pipeline leveraging advanced foundation models, namely GPT-4V and DALL-E 3. To ensure its high quality, diverse examples are first collected online, expanded, and then used to create high-quality diptychs featuring input and output images with detailed text prompts, followed by precise alignment ensured through post-processing. In addition, we propose two evaluation metrics, Alignment and Coherence, to quantitatively assess the quality of image edit pairs using GPT-4V. HQ-Edits high-resolution images, rich in detail and accompanied by comprehensive editing prompts, substantially enhance the capabilities of existing image editing models. For example, an HQ-Edit finetuned InstructPix2Pix can attain state-of-the-art image editing performance, even surpassing those models fine-tuned with human-annotated data. The project page is https://thefllood.github.io/HQEdit_web.

Fan Ma, Xiaojie Jin, Heng Wang et al.

Recent advances in large video-language models have displayed promising outcomes in video comprehension. Current approaches straightforwardly convert video into language tokens and employ large language models for multi-modal tasks. However, this method often leads to the generation of irrelevant content, commonly known as "hallucination", as the length of the text increases and the impact of the video diminishes. To address this problem, we propose Vista-LLaMA, a novel framework that maintains the consistent distance between all visual tokens and any language tokens, irrespective of the generated text length. Vista-LLaMA omits relative position encoding when determining attention weights between visual and text tokens, retaining the position encoding for text and text tokens. This amplifies the effect of visual tokens on text generation, especially when the relative distance is longer between visual and text tokens. The proposed attention mechanism significantly reduces the chance of producing irrelevant text related to the video content. Furthermore, we present a sequential visual projector that projects the current video frame into tokens of language space with the assistance of the previous frame. This approach not only captures the temporal relationship within the video, but also allows less visual tokens to encompass the entire video. Our approach significantly outperforms various previous methods (e.g., Video-ChatGPT, MovieChat) on four challenging open-ended video question answering benchmarks. We reach an accuracy of 60.7 on the zero-shot NExT-QA and 60.5 on the zero-shot MSRVTT-QA, setting a new state-of-the-art performance. This project is available at https://jinxxian.github.io/Vista-LLaMA.

Xuanchen Wang, Heng Wang, Weidong Cai

Music is both an auditory and an embodied phenomenon, closely linked to human motion and naturally expressed through dance. However, most existing audio representations neglect this embodied dimension, limiting their ability to capture rhythmic and structural cues that drive movement. We propose MotionBeat, a framework for motion-aligned music representation learning. MotionBeat is trained with two newly proposed objectives: the Embodied Contrastive Loss (ECL), an enhanced InfoNCE formulation with tempo-aware and beat-jitter negatives to achieve fine-grained rhythmic discrimination, and the Structural Rhythm Alignment Loss (SRAL), which ensures rhythm consistency by aligning music accents with corresponding motion events. Architecturally, MotionBeat introduces bar-equivariant phase rotations to capture cyclic rhythmic patterns and contact-guided attention to emphasize motion events synchronized with musical accents. Experiments show that MotionBeat outperforms state-of-the-art audio encoders in music-to-dance generation and transfers effectively to beat tracking, music tagging, genre and instrument classification, emotion recognition, and audio-visual retrieval. Our project demo page: https://motionbeat2025.github.io/.

Heng Wang, Chaoyi Zhang, Jianhui Yu et al.

Automatic 3D neuron reconstruction is critical for analysing the morphology and functionality of neurons in brain circuit activities. However, the performance of existing tracing algorithms is hinged by the low image quality. Recently, a series of deep learning based segmentation methods have been proposed to improve the quality of raw 3D optical image stacks by removing noises and restoring neuronal structures from low-contrast background. Due to the variety of neuron morphology and the lack of large neuron datasets, most of current neuron segmentation models rely on introducing complex and specially-designed submodules to a base architecture with the aim of encoding better feature representations. Though successful, extra burden would be put on computation during inference. Therefore, rather than modifying the base network, we shift our focus to the dataset itself. The encoder-decoder backbone used in most neuron segmentation models attends only intra-volume voxel points to learn structural features of neurons but neglect the shared intrinsic semantic features of voxels belonging to the same category among different volumes, which is also important for expressive representation learning. Hence, to better utilise the scarce dataset, we propose to explicitly exploit such intrinsic features of voxels through a novel voxel-level cross-volume representation learning paradigm on the basis of an encoder-decoder segmentation model. Our method introduces no extra cost during inference. Evaluated on 42 3D neuron images from BigNeuron project, our proposed method is demonstrated to improve the learning ability of the original segmentation model and further enhancing the reconstruction performance.

Heng Wang, Yang Song, Chaoyi Zhang et al.

One of the critical steps in improving accurate single neuron reconstruction from three-dimensional (3D) optical microscope images is the neuronal structure segmentation. However, they are always hard to segment due to the lack in quality. Despite a series of attempts to apply convolutional neural networks (CNNs) on this task, noise and disconnected gaps are still challenging to alleviate with the neglect of the non-local features of graph-like tubular neural structures. Hence, we present an end-to-end segmentation network by jointly considering the local appearance and the global geometry traits through graph reasoning and a skeleton-based auxiliary loss. The evaluation results on the Janelia dataset from the BigNeuron project demonstrate that our proposed method exceeds the counterpart algorithms in performance.

Heng Wang, Donghao Zhang, Yang Song et al.

Image-to-image translation is significant to many computer vision and machine learning tasks such as image synthesis and video synthesis. It has primary applications in the graphics editing and animation industries. With the development of generative adversarial networks, a lot of attention has been drawn to image-to-image translation tasks. In this paper, we propose and investigate a novel task named as panoptic-level image-to-image translation and a naive baseline of solving this task. Panoptic-level image translation extends the current image translation task to two separate objectives of semantic style translation (adjust the style of objects to that of different domains) and instance transfiguration (swap between different types of objects). The proposed task generates an image from a complete and detailed panoptic perspective which can enrich the context of real-world vision synthesis. Our contribution consists of the proposal of a significant task worth investigating and a naive baseline of solving it. The proposed baseline consists of the multiple instances sequential translation and semantic-level translation with domain-invariant content code.