arXiv subjects

Heng Wang

Publications and source records attributed to Heng Wang.

At least 127 records · Page 7Linked to original sources

arXiv2024

Dance Any Beat: Blending Beats with Visuals in Dance Video Generation

Generating dance from music is crucial for advancing automated choreography. Current methods typically produce skeleton keypoint sequences instead of dance videos and lack the capability to make specific individuals dance, which reduces their real-world applicability. These methods also require precise keypoint annotations, complicating data collection and limiting the use of self-collected video datasets. To overcome these challenges, we introduce a novel task: generating dance videos directly from images of individuals guided by music. This task enables the dance generation of specific individuals without requiring keypoint annotations, making it more versatile and applicable to various situations. Our solution, the Dance Any Beat Diffusion model (DabFusion), utilizes a reference image and a music piece to generate dance videos featuring various dance types and choreographies. The music is analyzed by our specially designed music encoder, which identifies essential features including dance style, movement, and rhythm. DabFusion excels in generating dance videos not only for individuals in the training dataset but also for any previously unseen person. This versatility stems from its approach of generating latent optical flow, which contains all necessary motion information to animate any person in the image. We evaluate DabFusion's performance using the AIST++ dataset, focusing on video quality, audio-video synchronization, and motion-music alignment. We propose a 2D Motion-Music Alignment Score (2D-MM Align), which builds on the Beat Alignment Score to more effectively evaluate motion-music alignment for this new task. Experiments show that our DabFusion establishes a solid baseline for this innovative task. Video results can be found on our project page: https://DabFusion.github.io.

cs.CV↗

arXiv2024

Real-time and Downtime-tolerant Fault Diagnosis for Railway Turnout Machines (RTMs) Empowered with Cloud-Edge Pipeline Parallelism

Railway Turnout Machines (RTMs) are mission-critical components of the railway transportation infrastructure, responsible for directing trains onto desired tracks. For safety assurance applications, especially in early-warning scenarios, RTM faults are expected to be detected as early as possible on a continuous 7x24 basis. However, limited emphasis has been placed on distributed model inference frameworks that can meet the inference latency and reliability requirements of such mission critical fault diagnosis systems. In this paper, an edge-cloud collaborative early-warning system is proposed to enable real-time and downtime-tolerant fault diagnosis of RTMs, providing a new paradigm for the deployment of models in safety-critical scenarios. Firstly, a modular fault diagnosis model is designed specifically for distributed deployment, which utilizes a hierarchical architecture consisting of the prior knowledge module, subordinate classifiers, and a fusion layer for enhanced accuracy and parallelism. Then, a cloud-edge collaborative framework leveraging pipeline parallelism, namely CEC-PA, is developed to minimize the overhead resulting from distributed task execution and context exchange by strategically partitioning and offloading model components across cloud and edge. Additionally, an election consensus mechanism is implemented within CEC-PA to ensure system robustness during coordinator node downtime. Comparative experiments and ablation studies are conducted to validate the effectiveness of the proposed distributed fault diagnosis approach. Our ensemble-based fault diagnosis model achieves a remarkable 97.4% accuracy on a real-world dataset collected by Nanjing Metro in Jiangsu Province, China. Meanwhile, CEC-PA demonstrates superior recovery proficiency during node disruptions and speed-up ranging from 1.98x to 7.93x in total inference time compared to its counterparts.

cs.NI↗

arXiv2024

Resolving Knowledge Conflicts in Large Language Models

Large language models (LLMs) often encounter knowledge conflicts, scenarios where discrepancy arises between the internal parametric knowledge of LLMs and non-parametric information provided in the prompt context. In this work we ask what are the desiderata for LLMs when a knowledge conflict arises and whether existing LLMs fulfill them. We posit that LLMs should 1) identify knowledge conflicts, 2) pinpoint conflicting information segments, and 3) provide distinct answers or viewpoints in conflicting scenarios. To this end, we introduce an evaluation framework for simulating contextual knowledge conflicts and quantitatively evaluating to what extent LLMs achieve these goals. It includes diverse and complex situations of knowledge conflict, knowledge from diverse entities and domains, two synthetic conflict creation methods, and settings with progressively increasing difficulty to reflect realistic knowledge conflicts. Extensive experiments with the framework reveal that while LLMs perform well in identifying the existence of knowledge conflicts, they struggle to determine the specific conflicting knowledge and produce a response with distinct answers amidst conflicting information. To address these challenges, we propose new instruction-based approaches that augment LLMs to better achieve the three goals. Further analysis shows that abilities to tackle knowledge conflicts are greatly impacted by factors such as knowledge domain, while generating robust responses to knowledge conflict scenarios remains an open research question.

cs.CL↗

arXiv2024

Exploring Annotation-free Image Captioning with Retrieval-augmented Pseudo Sentence Generation

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.

cs.CV↗

arXiv2024

Can LLM Graph Reasoning Generalize beyond Pattern Memorization?

Large language models (LLMs) demonstrate great potential for problems with implicit graphical structures, while recent works seek to enhance the graph reasoning capabilities of LLMs through specialized instruction tuning. The resulting 'graph LLMs' are evaluated with in-distribution settings only, thus it remains underexplored whether LLMs are learning generalizable graph reasoning skills or merely memorizing patterns in the synthetic training data. To this end, we propose the NLGift benchmark, an evaluation suite of LLM graph reasoning generalization: whether LLMs could go beyond semantic, numeric, structural, reasoning patterns in the synthetic training data and improve utility on real-world graph-based tasks. Extensive experiments with two LLMs across four graph reasoning tasks demonstrate that while generalization on simple patterns (semantic, numeric) is somewhat satisfactory, LLMs struggle to generalize across reasoning and real-world patterns, casting doubt on the benefit of synthetic graph tuning for real-world tasks with underlying network structures. We explore three strategies to improve LLM graph reasoning generalization, and we find that while post-training alignment is most promising for real-world tasks, empowering LLM graph reasoning to go beyond pattern memorization remains an open research question.

cs.CL↗

arXiv2024

Enhancing Advanced Visual Reasoning Ability of Large Language Models

Recent advancements in Vision-Language (VL) research have sparked new benchmarks for complex visual reasoning, challenging models' advanced reasoning ability. Traditional Vision-Language Models (VLMs) perform well in visual perception tasks while struggling with complex reasoning scenarios. Conversely, Large Language Models (LLMs) demonstrate robust text reasoning capabilities; however, they lack visual acuity. To bridge this gap, we propose Complex Visual Reasoning Large Language Models (CVR-LLM), capitalizing on VLMs' visual perception proficiency and LLMs' extensive reasoning capability. Unlike recent multimodal large language models (MLLMs) that require a projection layer, our approach transforms images into detailed, context-aware descriptions using an iterative self-refinement loop and leverages LLMs' text knowledge for accurate predictions without extra training. We also introduce a novel multi-modal in-context learning (ICL) methodology to enhance LLMs' contextual understanding and reasoning. Additionally, we introduce Chain-of-Comparison (CoC), a step-by-step comparison technique enabling contrasting various aspects of predictions. Our CVR-LLM presents the first comprehensive study across a wide array of complex visual reasoning tasks and achieves SOTA performance among all.

cs.CV↗

arXiv2024

VMAS: Video-to-Music Generation via Semantic Alignment in Web Music Videos

We present a framework for learning to generate background music from video inputs. Unlike existing works that rely on symbolic musical annotations, which are limited in quantity and diversity, our method leverages large-scale web videos accompanied by background music. This enables our model to learn to generate realistic and diverse music. To accomplish this goal, we develop a generative video-music Transformer with a novel semantic video-music alignment scheme. Our model uses a joint autoregressive and contrastive learning objective, which encourages the generation of music aligned with high-level video content. We also introduce a novel video-beat alignment scheme to match the generated music beats with the low-level motions in the video. Lastly, to capture fine-grained visual cues in a video needed for realistic background music generation, we introduce a new temporal video encoder architecture, allowing us to efficiently process videos consisting of many densely sampled frames. We train our framework on our newly curated DISCO-MV dataset, consisting of 2.2M video-music samples, which is orders of magnitude larger than any prior datasets used for video music generation. Our method outperforms existing approaches on the DISCO-MV and MusicCaps datasets according to various music generation evaluation metrics, including human evaluation. Results are available at https://genjib.github.io/project_page/VMAs/index.html

cs.MM↗

arXiv2024

Future Does Matter: Boosting 3D Object Detection with Temporal Motion Estimation in Point Cloud Sequences

Accurate and robust LiDAR 3D object detection is essential for comprehensive scene understanding in autonomous driving. Despite its importance, LiDAR detection performance is limited by inherent constraints of point cloud data, particularly under conditions of extended distances and occlusions. Recently, temporal aggregation has been proven to significantly enhance detection accuracy by fusing multi-frame viewpoint information and enriching the spatial representation of objects. In this work, we introduce a novel LiDAR 3D object detection framework, namely LiSTM, to facilitate spatial-temporal feature learning with cross-frame motion forecasting information. We aim to improve the spatial-temporal interpretation capabilities of the LiDAR detector by incorporating a dynamic prior, generated from a non-learnable motion estimation model. Specifically, Motion-Guided Feature Aggregation (MGFA) is proposed to utilize the object trajectory from previous and future motion states to model spatial-temporal correlations into gaussian heatmap over a driving sequence. This motion-based heatmap then guides the temporal feature fusion, enriching the proposed object features. Moreover, we design a Dual Correlation Weighting Module (DCWM) that effectively facilitates the interaction between past and prospective frames through scene- and channel-wise feature abstraction. In the end, a cascade cross-attention-based decoder is employed to refine the 3D prediction. We have conducted experiments on the Waymo and nuScenes datasets to demonstrate that the proposed framework achieves superior 3D detection performance with effective spatial-temporal feature learning.

cs.CV↗

arXiv2024

Digital Twin Channel for 6G: Concepts, Architectures and Potential Applications

Digital twin channel (DTC) is the real-time mapping of a wireless channel from the physical world to the digital world, which is expected to provide significant performance enhancements for the sixth-generation (6G) air-interface design. In this work, we first define five evolution levels of channel twins with the progression of wireless communication. The fifth level, autonomous DTC, is elaborated with multi-dimensional factors such as methodology, characterization precision, and data category. Then, we provide detailed insights into the requirements and architecture of a complete DTC for 6G. Subsequently, a sensing-enhanced real-time channel prediction platform and experimental validations are exhibited. Finally, drawing from the vision of the 6G network, we explore the potential applications and the open issues in future DTC research.

eess.SP↗

arXiv2024

Integrated high-performance error correction for continuous-variable quantum key distribution

An integrated error-correction scheme with high throughput, low frame errors rate (FER) and high reconciliation efficiency under low signal to noise ratio (SNR) is one of the major bottlenecks to realize high-performance and low-cost continuous variable quantum key distribution (CV-QKD). To solve this long-standing problem, a novel two-stage error correction method with limited precision that is suitable for integration given limited on-chip hardware resource while maintaining excellent decoding performance is proposed, and experimentally verified on a commercial FPGA. Compared to state-of-art results, the error-correction throughput can be improved more than one order of magnitude given FER<0.1 based on the proposed method, where 544.03 Mbps and 393.33 Mbps real-time error correction is achieved for typical 0.2 and 0.1 code rate, respectively. Besides, compared with traditional decoding method, the secure key rate (SKR) for CV-QKD under composable security framework can be improved by 140.09% and 122.03% by using the proposed two-stage decoding method for codes rate 0.2 and 0.1, which can support 32.70 Mbps and 5.66 Mbps real-time SKR under typical transmission distances of 25 km and 50 km, correspondingly. The record-breaking results paves the way for large-scale deployment of high-rate integrated CV-QKD systems in metropolitan quantum secure network.

quant-ph↗

arXiv2024

DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detection

Large language models are limited by challenges in factuality and hallucinations to be directly employed off-the-shelf for judging the veracity of news articles, where factual accuracy is paramount. In this work, we propose DELL that identifies three key stages in misinformation detection where LLMs could be incorporated as part of the pipeline: 1) LLMs could \emph{generate news reactions} to represent diverse perspectives and simulate user-news interaction networks; 2) LLMs could \emph{generate explanations} for proxy tasks (e.g., sentiment, stance) to enrich the contexts of news articles and produce experts specializing in various aspects of news understanding; 3) LLMs could \emph{merge task-specific experts} and provide an overall prediction by incorporating the predictions and confidence scores of varying experts. Extensive experiments on seven datasets with three LLMs demonstrate that DELL outperforms state-of-the-art baselines by up to 16.8\% in macro f1-score. Further analysis reveals that the generated reactions and explanations are greatly helpful in misinformation detection, while our proposed LLM-guided expert merging helps produce better-calibrated predictions.

cs.CL↗

arXiv2024

Secure Combination of Untrusted Time information Based on Optimized Dempster-Shafer Theory

Secure precision time synchronization is important for applications of Cyber-Physical Systems. However, several attacks, especially the Time Delay Attack (TDA), deteriorates the performance of time synchronization system seriously. Multiple paths scheme is thought as an effective security countermeasure to decrease the influence of TDA. However, the effective secure combination algorithm is still missed for precision time synchronization. In this paper, a secure combination algorithm based on Dempster-Shafer theory is proposed for multiple paths method. Special optimizations are done for the combination algorithm to solve the potential problems due to untrusted evidence. Theoretical simulation shows that the proposed algorithm works much better than Fault Tolerant Algorithm (FTA) and the attack detection method based on single path. And experimental demonstration proves the feasibility and superiority of the proposed algorithm, where the time stability with 27.97 ps, 1.57 ps, and 1.12 ps at average time 1s, 10s, 100s is achieved under TDA and local clock jump. The proposed algorithm can be used to improve the security and resilience of many importance synchronization protocol, such as NTP, PTP, and TWFTT.

cs.CR↗

arXiv2024

Custom Cloth Creation and Virtual Try-on for Everyone

This demo showcases a simple tool that utilizes AIGC technology, enabling both professional designers and regular users to easily customize clothing for their digital avatars. Customization options include changing clothing colors, textures, logos, and patterns. Compared with traditional 3D modeling processes, our approach significantly enhances efficiency and interactivity and reduces production costs.

cs.HC↗

arXiv2024

Autoregressive Pretraining with Mamba in Vision

The vision community has started to build with the recently developed state space model, Mamba, as the new backbone for a range of tasks. This paper shows that Mamba's visual capability can be significantly enhanced through autoregressive pretraining, a direction not previously explored. Efficiency-wise, the autoregressive nature can well capitalize on the Mamba's unidirectional recurrent structure, enabling faster overall training speed compared to other training strategies like mask modeling. Performance-wise, autoregressive pretraining equips the Mamba architecture with markedly higher accuracy over its supervised-trained counterparts and, more importantly, successfully unlocks its scaling potential to large and even huge model sizes. For example, with autoregressive pretraining, a base-size Mamba attains 83.2\% ImageNet accuracy, outperforming its supervised counterpart by 2.0\%; our huge-size Mamba, the largest Vision Mamba to date, attains 85.0\% ImageNet accuracy (85.5\% when finetuned with $384\times384$ inputs), notably surpassing all other Mamba variants in vision. The code is available at \url{https://github.com/OliverRensu/ARM}.

cs.CV↗

arXiv2024

Progressive Volume Distillation with Active Learning for Efficient NeRF Architecture Conversion

Neural Radiance Fields (NeRF) have been widely adopted as practical and versatile representations for 3D scenes, facilitating various downstream tasks. However, different architectures, including the plain Multi-Layer Perceptron (MLP), Tensors, low-rank Tensors, Hashtables, and their combinations, entail distinct trade-offs. For instance, representations based on Hashtables enable faster rendering but lack clear geometric meaning, thereby posing challenges for spatial-relation-aware editing. To address this limitation and maximize the potential of each architecture, we propose Progressive Volume Distillation with Active Learning (PVD-AL), a systematic distillation method that enables any-to-any conversion between diverse architectures. PVD-AL decomposes each structure into two parts and progressively performs distillation from shallower to deeper volume representation, leveraging effective information retrieved from the rendering process. Additionally, a three-level active learning technique provides continuous feedback from teacher to student during the distillation process, achieving high-performance outcomes. Experimental evidence showcases the effectiveness of our method across multiple benchmark datasets. For instance, PVD-AL can distill an MLP-based model from a Hashtables-based model at a 10~20X faster speed and 0.8dB~2dB higher PSNR than training the MLP-based model from scratch. Moreover, PVD-AL permits the fusion of diverse features among distinct structures, enabling models with multiple editing properties and providing a more efficient model to meet real-time requirements like mobile devices. Project website: https://sk-fun.fun/PVD-AL.

cs.CV↗

arXiv2024

Open-world Instance Segmentation: Top-down Learning with Bottom-up Supervision

Many top-down architectures for instance segmentation achieve significant success when trained and tested on pre-defined closed-world taxonomy. However, when deployed in the open world, they exhibit notable bias towards seen classes and suffer from significant performance drop. In this work, we propose a novel approach for open world instance segmentation called bottom-Up and top-Down Open-world Segmentation (UDOS) that combines classical bottom-up segmentation algorithms within a top-down learning framework. UDOS first predicts parts of objects using a top-down network trained with weak supervision from bottom-up segmentations. The bottom-up segmentations are class-agnostic and do not overfit to specific taxonomies. The part-masks are then fed into affinity-based grouping and refinement modules to predict robust instance-level segmentations. UDOS enjoys both the speed and efficiency from the top-down architectures and the generalization ability to unseen categories from bottom-up supervision. We validate the strengths of UDOS on multiple cross-category as well as cross-dataset transfer tasks from 5 challenging datasets including MS-COCO, LVIS, ADE20k, UVO and OpenImages, achieving significant improvements over state-of-the-art across the board. Our code and models are available on our project page.

cs.CV↗

arXiv2024

Boosting 3D Neuron Segmentation with 2D Vision Transformer Pre-trained on Natural Images

Neuron reconstruction, one of the fundamental tasks in neuroscience, rebuilds neuronal morphology from 3D light microscope imaging data. It plays a critical role in analyzing the structure-function relationship of neurons in the nervous system. However, due to the scarcity of neuron datasets and high-quality SWC annotations, it is still challenging to develop robust segmentation methods for single neuron reconstruction. To address this limitation, we aim to distill the consensus knowledge from massive natural image data to aid the segmentation model in learning the complex neuron structures. Specifically, in this work, we propose a novel training paradigm that leverages a 2D Vision Transformer model pre-trained on large-scale natural images to initialize our Transformer-based 3D neuron segmentation model with a tailored 2D-to-3D weight transferring strategy. Our method builds a knowledge sharing connection between the abundant natural and the scarce neuron image domains to improve the 3D neuron segmentation ability in a data-efficiency manner. Evaluated on a popular benchmark, BigNeuron, our method enhances neuron segmentation performance by 8.71% over the model trained from scratch with the same amount of training samples.

cs.CV↗

arXiv2024

HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing

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.

cs.CV↗