Search

Fashion image editing is a crucial tool for designers to convey their creative ideas by visualizing design concepts interactively. Current fashion image editing techniques, though advanced with multimodal prompts and powerful diffusion models, often struggle to accurately identify editing regions and preserve the desired garment texture detail. To address these challenges, we introduce a new multimodal fashion image editing architecture based on latent diffusion models, called Detail-Preserved Diffusion Models (DPDEdit). DPDEdit guides the fashion image generation of diffusion models by integrating text prompts, region masks, human pose images, and garment texture images. To precisely locate the editing region, we first introduce Grounded-SAM to predict the editing region based on the user's textual description, and then combine it with other conditions to perform local editing. To transfer the detail of the given garment texture into the target fashion image, we propose a texture injection and refinement mechanism. Specifically, this mechanism employs a decoupled cross-attention layer to integrate textual descriptions and texture images, and incorporates an auxiliary U-Net to preserve the high-frequency details of generated garment texture. Additionally, we extend the VITON-HD dataset using a multimodal large language model to generate paired samples with texture images and textual descriptions. Extensive experiments show that our DPDEdit outperforms state-of-the-art methods in terms of image fidelity and coherence with the given multimodal inputs., Comment: 13 pages,12 figures

Combining Vision Large Language Models (VLLMs) with diffusion models offers a powerful method for executing image editing tasks based on human language instructions. However, language instructions alone often fall short in accurately conveying user requirements, particularly when users want to add, replace elements in specific areas of an image. Luckily, masks can effectively indicate the exact locations or elements to be edited, while they require users to precisely draw the shapes at the desired locations, which is highly user-unfriendly. To address this, we propose FlexEdit, an end-to-end image editing method that leverages both free-shape masks and language instructions for Flexible Editing. Our approach employs a VLLM in comprehending the image content, mask, and user instructions. Additionally, we introduce the Mask Enhance Adapter (MEA) that fuses the embeddings of the VLLM with the image data, ensuring a seamless integration of mask information and model output embeddings. Furthermore, we construct FSMI-Edit, a benchmark specifically tailored for free-shape mask, including 8 types of free-shape mask. Extensive experiments show that our method achieves state-of-the-art (SOTA) performance in LLM-based image editing, and our simple prompting technique stands out in its effectiveness. The code and data can be found at https://github.com/A-new-b/flex_edit., Comment: 15 pages, 14 figures

Hindustani music is a performance-driven oral tradition that exhibits the rendition of rich melodic patterns. In this paper, we focus on generative modeling of singers' vocal melodies extracted from audio recordings, as the voice is musically prominent within the tradition. Prior generative work in Hindustani music models melodies as coarse discrete symbols which fails to capture the rich expressive melodic intricacies of singing. Thus, we propose to use a finely quantized pitch contour, as an intermediate representation for hierarchical audio modeling. We propose GaMaDHaNi, a modular two-level hierarchy, consisting of a generative model on pitch contours, and a pitch contour to audio synthesis model. We compare our approach to non-hierarchical audio models and hierarchical models that use a self-supervised intermediate representation, through a listening test and qualitative analysis. We also evaluate audio model's ability to faithfully represent the pitch contour input using Pearson correlation coefficient. By using pitch contours as an intermediate representation, we show that our model may be better equipped to listen and respond to musicians in a human-AI collaborative setting by highlighting two potential interaction use cases (1) primed generation, and (2) coarse pitch conditioning., Comment: Accepted at International Society for Music Information Retrieval (ISMIR) 2024

A quantum network provides an infrastructure connecting quantum devices with revolutionary computing, sensing, and communication capabilities. As the best-known application of a quantum network, quantum key distribution (QKD) shares secure keys guaranteed by the laws of quantum mechanics. A quantum satellite constellation offers a solution to facilitate the quantum network on a global scale. The Micius satellite has verified the feasibility of satellite quantum communications, however, scaling up quantum satellite constellations is challenging, requiring small lightweight satellites, portable ground stations and real-time secure key exchange. Here we tackle these challenges and report the development of a quantum microsatellite capable of performing space-to-ground QKD using portable ground stations. The quantum microsatellite features a payload weighing approximately 23 kg, while the portable ground station weighs about 100 kg. These weights represent reductions by more than an order and two orders of magnitude, respectively, compared to the Micius satellite. Additionally, we multiplex bidirectional satellite-ground optical communication with quantum communication, enabling key distillation and secure communication in real-time. Using the microsatellite and the portable ground stations, we demonstrate satellite-based QKD with multiple ground stations and achieve the sharing of up to 0.59 million bits of secure keys during a single satellite pass. The compact quantum payload can be readily assembled on existing space stations or small satellites, paving the way for a satellite-constellation-based quantum and classical network for widespread real-life applications., Comment: 40 pages, 8 figures

This paper presents our winning approach for the MER-NOISE and MER-OV tracks of the MER2024 Challenge on multimodal emotion recognition. Our system leverages the advanced emotional understanding capabilities of Emotion-LLaMA to generate high-quality annotations for unlabeled samples, addressing the challenge of limited labeled data. To enhance multimodal fusion while mitigating modality-specific noise, we introduce Conv-Attention, a lightweight and efficient hybrid framework. Extensive experimentation vali-dates the effectiveness of our approach. In the MER-NOISE track, our system achieves a state-of-the-art weighted average F-score of 85.30%, surpassing the second and third-place teams by 1.47% and 1.65%, respectively. For the MER-OV track, our utilization of Emotion-LLaMA for open-vocabulary annotation yields an 8.52% improvement in average accuracy and recall compared to GPT-4V, securing the highest score among all participating large multimodal models. The code and model for Emotion-LLaMA are available at https://github.com/ZebangCheng/Emotion-LLaMA., Comment: Ranked 1st in MER24@IJCAI and MRAC24@ACM MM (MER-NOISE & MER-OV (self-evaluated))

In this paper, we propose a novel framework, Combo, for harmonious co-speech holistic 3D human motion generation and efficient customizable adaption. In particular, we identify that one fundamental challenge as the multiple-input-multiple-output (MIMO) nature of the generative model of interest. More concretely, on the input end, the model typically consumes both speech signals and character guidance (e.g., identity and emotion), which not only poses challenge on learning capacity but also hinders further adaptation to varying guidance; on the output end, holistic human motions mainly consist of facial expressions and body movements, which are inherently correlated but non-trivial to coordinate in current data-driven generation process. In response to the above challenge, we propose tailored designs to both ends. For the former, we propose to pre-train on data regarding a fixed identity with neutral emotion, and defer the incorporation of customizable conditions (identity and emotion) to fine-tuning stage, which is boosted by our novel X-Adapter for parameter-efficient fine-tuning. For the latter, we propose a simple yet effective transformer design, DU-Trans, which first divides into two branches to learn individual features of face expression and body movements, and then unites those to learn a joint bi-directional distribution and directly predicts combined coefficients. Evaluated on BEAT2 and SHOW datasets, Combo is highly effective in generating high-quality motions but also efficient in transferring identity and emotion. Project website: \href{https://xc-csc101.github.io/combo/}{Combo}.

The electric vehicle (EV) battery supply chain's vulnerability to disruptions necessitates advanced predictive analytics. We present SHIELD (Schema-based Hierarchical Induction for EV supply chain Disruption), a system integrating Large Language Models (LLMs) with domain expertise for EV battery supply chain risk assessment. SHIELD combines: (1) LLM-driven schema learning to construct a comprehensive knowledge library, (2) a disruption analysis system utilizing fine-tuned language models for event extraction, multi-dimensional similarity matching for schema matching, and Graph Convolutional Networks (GCNs) with logical constraints for prediction, and (3) an interactive interface for visualizing results and incorporating expert feedback to enhance decision-making. Evaluated on 12,070 paragraphs from 365 sources (2022-2023), SHIELD outperforms baseline GCNs and LLM+prompt methods (e.g., GPT-4o) in disruption prediction. These results demonstrate SHIELD's effectiveness in combining LLM capabilities with domain expertise for enhanced supply chain risk assessment., Comment: 30 pages, 11 figures, Project: https://f1y1113.github.io/MFI/

The entangled photons are crucial resources for quantum communications and networking. Here, we present an ultra-bright polarization-entangled photon source based on a periodically poled lithium niobate waveguide designed for practical quantum communication networks. Using a 780 nm pump laser, the source achieves a pair generation rate of 2.4 $\times 10^{10}$ pairs/s/mW. This work has achieved a directly measured power of 17.9 nW in entangled photon generation with a 3.2 mW pump power. Based on this, we demonstrate the practicality of the source by conducting quantum key distribution experiments over long-distance fiber links, achieving the applicable secure key rates of up to 440.80 bits/s over 200 km with 62 dB loss and reaching a maximum secure key generation distance of 404 km. These results demonstrate the potential of wavelength-multiplexed polarization-entangled photon sources for high-speed, long-distance quantum communication, positioning them as key components for future large-scale quantum networks., Comment: 18 pages, 6 figures

Dataset Distillation aims to compress a large dataset into a significantly more compact, synthetic one without compromising the performance of the trained models. To achieve this, existing methods use the agent model to extract information from the target dataset and embed it into the distilled dataset. Consequently, the quality of extracted and embedded information determines the quality of the distilled dataset. In this work, we find that existing methods introduce misaligned information in both information extraction and embedding stages. To alleviate this, we propose Prioritize Alignment in Dataset Distillation (PAD), which aligns information from the following two perspectives. 1) We prune the target dataset according to the compressing ratio to filter the information that can be extracted by the agent model. 2) We use only deep layers of the agent model to perform the distillation to avoid excessively introducing low-level information. This simple strategy effectively filters out misaligned information and brings non-trivial improvement for mainstream matching-based distillation algorithms. Furthermore, built on trajectory matching, \textbf{PAD} achieves remarkable improvements on various benchmarks, achieving state-of-the-art performance., Comment: 18 pages, 9 figures

The emergence of quantum mechanics and general relativity has transformed our understanding of the natural world significantly. However, integrating these two theories presents immense challenges, and their interplay remains untested. Recent theoretical studies suggest that the single-photon interference covering huge space can effectively probe the interface between quantum mechanics and general relativity. We developed an alternative design using unbalanced Michelson interferometers to address this and validated its feasibility over an 8.4 km free-space channel. Using a high-brightness single-photon source based on quantum dots, we demonstrated single-photon interference along this long-distance baseline. We achieved a phase measurement precision of 16.2 mrad, which satisfied the measurement requirements for a gravitational redshift at the geosynchronous orbit by five times the standard deviation. Our results confirm the feasibility of the single-photon version of the Colella-Overhauser-Werner experiment for testing the quantum effects in curved spacetime., Comment: 22 pages, 6 figures

In today's music industry, album cover design is as crucial as the music itself, reflecting the artist's vision and brand. However, many AI-driven album cover services require subscriptions or technical expertise, limiting accessibility. To address these challenges, we developed Music2P, an open-source, multi-modal AI-driven tool that streamlines album cover creation, making it efficient, accessible, and cost-effective through Ngrok. Music2P automates the design process using techniques such as Bootstrapping Language Image Pre-training (BLIP), music-to-text conversion (LP-music-caps), image segmentation (LoRA), and album cover and QR code generation (ControlNet). This paper demonstrates the Music2P interface, details our application of these technologies, and outlines future improvements. Our ultimate goal is to provide a tool that empowers musicians and producers, especially those with limited resources or expertise, to create compelling album covers., Comment: Accepted at CIKM 2024 Demo Paper track. Project available at https://github.com/JC-78/Music2P

Frequency tunable qubit plays a significant role for scalable superconducting quantum processors. The state-of-the-art room-temperature electronics for tuning qubit frequency suffers from unscalable limit, such as heating problem, linear growth of control cables, etc. Here we propose a scalable scheme to tune the qubit frequency by using in situ superconducting circuit, which is based on radio frequency superconducting quantum interference device (rf-SQUID). We demonstrate both theoretically and experimentally that the qubit frequency could be modulated by inputting several single pulses into rf-SQUID. Compared with the traditional scheme, our scheme not only solves the heating problem, but also provides the potential to exponentially reduce the number of cables inside the dilute refrigerator and the room-temperature electronics resource for tuning qubit frequency, which is achieved by a time-division-multiplex (TDM) scheme combining rf-SQUID with switch arrays. With such TDM scheme, the number of cables could be reduced from the usual $\sim 3n$ to $\sim \log_2{(3n)} + 1$ for two-dimensional quantum processors comprising $n$ qubits and $\sim 2n$ couplers. Our work paves the way for large-scale control of superconducting quantum processor., Comment: 9 pages, 6 figures

With the surge of large-scale pre-trained models (PTMs), adapting these models to numerous downstream tasks becomes a crucial problem. Consequently, parameter-efficient transfer learning (PETL) of large models has grasped huge attention. While PETL methods show impressive performance, they commonly rely on two optimistic assumptions: 1) the entire parameters of a PTM are available, and 2) a sufficiently large memory capacity is equipped for caching all the intermediate activations to compute gradients. However, in most real-world applications, PTMs are served as black-box APIs or proprietary software without explicit parameter accessibility. Besides, it is hard to meet a large memory requirement for modern PTMs. This work proposes black-box visual prompting (BlackVIP), which efficiently adapts the PTMs without knowledge about model architectures and parameters. BlackVIP has two components; 1) Coordinator and 2) simultaneous perturbation stochastic approximation with gradient correction (SPSA-GC). The Coordinator designs input-dependent visual prompts, which allow the target PTM to adapt in the wild. SPSA-GC efficiently estimates the gradient of PTM to update the Coordinator. Besides, we propose a variant, BlackVIP-SE, which significantly reduces the runtime and computational cost of BlackVIP. Extensive experiments on 19 datasets demonstrate that BlackVIPs enable robust adaptation to diverse domains and tasks with minimal memory requirements. We further provide theoretical analysis on the generalization of visual prompting methods by presenting their connection to the certified robustness of randomized smoothing., Comment: Extended work from the CVPR'23 paper: arxiv:2303.14773; This paper has been submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) for possible publication

MetaDesigner revolutionizes artistic typography synthesis by leveraging the strengths of Large Language Models (LLMs) to drive a design paradigm centered around user engagement. At the core of this framework lies a multi-agent system comprising the Pipeline, Glyph, and Texture agents, which collectively enable the creation of customized WordArt, ranging from semantic enhancements to the imposition of complex textures. MetaDesigner incorporates a comprehensive feedback mechanism that harnesses insights from multimodal models and user evaluations to refine and enhance the design process iteratively. Through this feedback loop, the system adeptly tunes hyperparameters to align with user-defined stylistic and thematic preferences, generating WordArt that not only meets but exceeds user expectations of visual appeal and contextual relevance. Empirical validations highlight MetaDesigner's capability to effectively serve diverse WordArt applications, consistently producing aesthetically appealing and context-sensitive results., Comment: 18 pages, 16 figures, Project: https://modelscope.cn/studios/WordArt/WordArt

Vision-and-Language Navigation (VLN) aims to develop embodied agents that navigate based on human instructions. However, current VLN frameworks often rely on static environments and optimal expert supervision, limiting their real-world applicability. To address this, we introduce Human-Aware Vision-and-Language Navigation (HA-VLN), extending traditional VLN by incorporating dynamic human activities and relaxing key assumptions. We propose the Human-Aware 3D (HA3D) simulator, which combines dynamic human activities with the Matterport3D dataset, and the Human-Aware Room-to-Room (HA-R2R) dataset, extending R2R with human activity descriptions. To tackle HA-VLN challenges, we present the Expert-Supervised Cross-Modal (VLN-CM) and Non-Expert-Supervised Decision Transformer (VLN-DT) agents, utilizing cross-modal fusion and diverse training strategies for effective navigation in dynamic human environments. A comprehensive evaluation, including metrics considering human activities, and systematic analysis of HA-VLN's unique challenges, underscores the need for further research to enhance HA-VLN agents' real-world robustness and adaptability. Ultimately, this work provides benchmarks and insights for future research on embodied AI and Sim2Real transfer, paving the way for more realistic and applicable VLN systems in human-populated environments., Comment: 30 pages, 18 figures, Project Page: https://lpercc.github.io/HA3D_simulator/

Accurate emotion perception is crucial for various applications, including human-computer interaction, education, and counseling. However, traditional single-modality approaches often fail to capture the complexity of real-world emotional expressions, which are inherently multimodal. Moreover, existing Multimodal Large Language Models (MLLMs) face challenges in integrating audio and recognizing subtle facial micro-expressions. To address this, we introduce the MERR dataset, containing 28,618 coarse-grained and 4,487 fine-grained annotated samples across diverse emotional categories. This dataset enables models to learn from varied scenarios and generalize to real-world applications. Furthermore, we propose Emotion-LLaMA, a model that seamlessly integrates audio, visual, and textual inputs through emotion-specific encoders. By aligning features into a shared space and employing a modified LLaMA model with instruction tuning, Emotion-LLaMA significantly enhances both emotional recognition and reasoning capabilities. Extensive evaluations show Emotion-LLaMA outperforms other MLLMs, achieving top scores in Clue Overlap (7.83) and Label Overlap (6.25) on EMER, an F1 score of 0.9036 on MER2023 challenge, and the highest UAR (45.59) and WAR (59.37) in zero-shot evaluations on DFEW dataset., Comment: 37 pages, 12 figures, Project: https://github.com/ZebangCheng/Emotion-LLaMA, Demo: https://huggingface.co/spaces/ZebangCheng/Emotion-LLaMA

In this paper, we present novel identification strategies to develop a unified framework for vortex-induced vibration (VIV) prediction based on the general semi-empirical wake oscillator. Greybox nonlinear system identification method accompanying high-fidelity computational fluid dynamics (CFD) and/or experimental data could be applied for the identification process. The proposed template of general wake oscillators contains low- to high-order damping terms to be identified for characterizing the possible flow dynamics. Two different strategies, including individual identification of single wake oscillator and overall identification of coupled VIV control equations, are proposed. VIV system consisting of an elastically-mounted circular cylinder submerged in laminar flow at Reynold number of 100 is considered. Both strategies have been tested and have exhibited high accuracy. The second strategy, i.e., overall identification of coupled VIV control equations, would be more suitable for the future framework owing that its training process considers the effect of fluid damping. A detailed mathematical introduction to future works on framework development covering the wide Reynold number range is addressed. The proposed unified framework is a landmark update of past wake oscillators both in terms of prediction accuracy and physical principles and has considerable research significance and practical engineering value., Comment: This version is not intended to be sent for peer review and is merely a summary of the preliminary work

Single-photon sources are essential for quantum networks, enabling applications ranging from quantum key distribution (QKD) to the burgeoning quantum internet. Despite the remarkable advancements, the current reliance of QKD on attenuated coherent (laser) light sources has imposed a fundamental limit on the secret key rate (SKR). This constraint is primarily attributable to the scarcity of single-photon components within coherent light, confined by an inherent upper bound of 1/e. Here, we report high-rate QKD using a high-efficiency single-photon source, enabling an SKR transcending the fundamental rate limit of coherent light. We developed an on-demand, bright semiconductor quantum-dot single-photon source with an efficiency of 0.71(2), exceeding the inherent bound of coherent light by approximately 2.87 dB. Implementing narrow-bandwidth filtering and random polarization modulation, we conducted a field QKD trial over a 14.6(1.1)-dB-loss free-space urban channel, achieving an SKR of 0.00108 bits per pulse. This surpasses the practical limit of coherent-light-based QKD by 2.53 dB. Our findings conclusively demonstrate the superior performance of nanotechnology-based single-photon sources over coherent light for QKD applications, marking a pivotal stride towards the realization of a global quantum internet., Comment: 22 pages, 5 figures, 1 Table

The flow-induced vibration and cavitation dynamics of three-dimensional flow past a cantilever flexible hydrofoil are investigated using a large eddy simulation (LES) model, a homogeneous mixture cavitation model and the structural modes superposition method. The present work aims to explore a potential mechanism responsible for a propeller singing behavior, and thus focuses on the synchronized hydroelastic coupling among the pressure pulsation inside the flow field, the cavitation generation and the structural vibration. To begin, we validate the tip vortex dynamics of a flexible hydrofoil against the available experimental. Our results demonstrate that the tip vortex shedding and the blade vibration are responsible for the intense peak in the low-frequency tonal components of the noise source, and the trailing-edge vortex shedding induces broadband components. Additionally, the generation of sheet cavitation induces considerable synchronized hydrofoil vibration (subjected to a flutter-like response), and affects the pressure fluctuations in the flow field, which further dominate the features of the underwater noise sources. It is suggested that the cavitation behavior and structural vibrations co-dominate the characteristics of singing noise from a propeller blade.

Despite impressive advancements in diffusion-based video editing models in altering video attributes, there has been limited exploration into modifying motion information while preserving the original protagonist's appearance and background. In this paper, we propose MotionFollower, a lightweight score-guided diffusion model for video motion editing. To introduce conditional controls to the denoising process, MotionFollower leverages two of our proposed lightweight signal controllers, one for poses and the other for appearances, both of which consist of convolution blocks without involving heavy attention calculations. Further, we design a score guidance principle based on a two-branch architecture, including the reconstruction and editing branches, which significantly enhance the modeling capability of texture details and complicated backgrounds. Concretely, we enforce several consistency regularizers and losses during the score estimation. The resulting gradients thus inject appropriate guidance to the intermediate latents, forcing the model to preserve the original background details and protagonists' appearances without interfering with the motion modification. Experiments demonstrate the competitive motion editing ability of MotionFollower qualitatively and quantitatively. Compared with MotionEditor, the most advanced motion editing model, MotionFollower achieves an approximately 80% reduction in GPU memory while delivering superior motion editing performance and exclusively supporting large camera movements and actions., Comment: 23 pages, 18 figures. Project page at https://francis-rings.github.io/MotionFollower/

The present work aims to study the cavitating turbulent flow of a full-scale marine propeller and explore the physical mechanism underpinning the underwater radiated noise. We employ the standard dynamic large eddy simulation for the turbulent wake flow and the Schnerr-Sauer cavitation model, while the Ffowcs-Williams-Hawkings acoustic analogy is considered for the hydroacoustic modeling. For the current investigation, we consider a well-known Potsdam Propeller Test Case to analyze the turbulent cavitating flow and the associated hydroacoustic emissions. To begin, the modeling framework is validated using the available experimental data, and distinctive double-helical tip vortex cavitation and its qualitative patterns along the vortex trajectory are captured. In comparison to the non-cavitating condition, the pressure distribution on the propeller surface is more disordered for the cavitating condition, which is further reflected by a relatively stronger power of both low-frequency tonal peaks and high-frequency broadband components in the spectrum of thrust generation. Specifically, the generation of cavitation leads to the enhancement of the monopole noise source and the breakdown of cavitation bubbles as well as vortex structures in the turbulent wake. Furthermore, the tonal noise with the frequency corresponding to the harmonics of blade passing frequency is also enhanced. Generally speaking, the generation of cavitation structures enhances the hydroacoustics energy of URN at all orientations, especially in the downstream direction with sound pressure level increasing up to 20 dB.

Emotional Text-to-Speech (E-TTS) synthesis has gained significant attention in recent years due to its potential to enhance human-computer interaction. However, current E-TTS approaches often struggle to capture the complexity of human emotions, primarily relying on oversimplified emotional labels or single-modality inputs. To address these limitations, we propose the Multimodal Emotional Text-to-Speech System (MM-TTS), a unified framework that leverages emotional cues from multiple modalities to generate highly expressive and emotionally resonant speech. MM-TTS consists of two key components: (1) the Emotion Prompt Alignment Module (EP-Align), which employs contrastive learning to align emotional features across text, audio, and visual modalities, ensuring a coherent fusion of multimodal information; and (2) the Emotion Embedding-Induced TTS (EMI-TTS), which integrates the aligned emotional embeddings with state-of-the-art TTS models to synthesize speech that accurately reflects the intended emotions. Extensive evaluations across diverse datasets demonstrate the superior performance of MM-TTS compared to traditional E-TTS models. Objective metrics, including Word Error Rate (WER) and Character Error Rate (CER), show significant improvements on ESD dataset, with MM-TTS achieving scores of 7.35% and 3.07%, respectively. Subjective assessments further validate that MM-TTS generates speech with emotional fidelity and naturalness comparable to human speech. Our code and pre-trained models are publicly available at https://anonymous.4open.science/r/MMTTS-D214

Semi-supervised learning has emerged as a promising approach to tackle the challenge of label scarcity in facial expression recognition (FER) task. However, current state-of-the-art methods primarily focus on one side of the coin, i.e., generating high-quality pseudo-labels, while overlooking the other side: enhancing expression-relevant representations. In this paper, we unveil both sides of the coin by proposing a unified framework termed hierarchicaL dEcoupling And Fusing (LEAF) to coordinate expression-relevant representations and pseudo-labels for semi-supervised FER. LEAF introduces a hierarchical expression-aware aggregation strategy that operates at three levels: semantic, instance, and category. (1) At the semantic and instance levels, LEAF decouples representations into expression-agnostic and expression-relevant components, and adaptively fuses them using learnable gating weights. (2) At the category level, LEAF assigns ambiguous pseudo-labels by decoupling predictions into positive and negative parts, and employs a consistency loss to ensure agreement between two augmented views of the same image. Extensive experiments on benchmark datasets demonstrate that by unveiling and harmonizing both sides of the coin, LEAF outperforms state-of-the-art semi-supervised FER methods, effectively leveraging both labeled and unlabeled data. Moreover, the proposed expression-aware aggregation strategy can be seamlessly integrated into existing semi-supervised frameworks, leading to significant performance gains. Our code is available at https://anonymous.4open.science/r/LEAF-BC57/.

This paper presents our winning submission to Subtask 2 of SemEval 2024 Task 3 on multimodal emotion cause analysis in conversations. We propose a novel Multimodal Emotion Recognition and Multimodal Emotion Cause Extraction (MER-MCE) framework that integrates text, audio, and visual modalities using specialized emotion encoders. Our approach sets itself apart from top-performing teams by leveraging modality-specific features for enhanced emotion understanding and causality inference. Experimental evaluation demonstrates the advantages of our multimodal approach, with our submission achieving a competitive weighted F1 score of 0.3435, ranking third with a margin of only 0.0339 behind the 1st team and 0.0025 behind the 2nd team. Project: https://github.com/MIPS-COLT/MER-MCE.git, Comment: Ranked 3rd in SemEval '24 Task 3 with F1 of 0.3435, close to 1st & 2nd by 0.0339 & 0.0025

Video Action Counting (VAC) is crucial in analyzing sports, fitness, and everyday activities by quantifying repetitive actions in videos. However, traditional VAC methods have overlooked the complexity of action repetitions, such as interruptions and the variability in cycle duration. Our research addresses the shortfall by introducing a novel approach to VAC, called Irregular Video Action Counting (IVAC). IVAC prioritizes modeling irregular repetition patterns in videos, which we define through two primary aspects: Inter-cycle Consistency and Cycle-interval Inconsistency. Inter-cycle Consistency ensures homogeneity in the spatial-temporal representations of cycle segments, signifying action uniformity within cycles. Cycle-interval inconsistency highlights the importance of distinguishing between cycle segments and intervals based on their inherent content differences. To encapsulate these principles, we propose a new methodology that includes consistency and inconsistency modules, supported by a unique pull-push loss (P2L) mechanism. The IVAC-P2L model applies a pull loss to promote coherence among cycle segment features and a push loss to clearly distinguish features of cycle segments from interval segments. Empirical evaluations conducted on the RepCount dataset demonstrate that the IVAC-P2L model sets a new benchmark in VAC task performance. Furthermore, the model demonstrates exceptional adaptability and generalization across various video contents, outperforming existing models on two additional datasets, UCFRep and Countix, without the need for dataset-specific optimization. These results confirm the efficacy of our approach in addressing irregular repetitions in videos and pave the way for further advancements in video analysis and understanding., Comment: Source code: https://github.com/hwang-cs-ime/IVAC-P2L

The advancement of autonomous driving systems hinges on the ability to achieve low-latency and high-accuracy perception. To address this critical need, this paper introduces Dynamic Routering Network (DyRoNet), a low-rank enhanced dynamic routing framework designed for streaming perception in autonomous driving systems. DyRoNet integrates a suite of pre-trained branch networks, each meticulously fine-tuned to function under distinct environmental conditions. At its core, the framework offers a speed router module, developed to assess and route input data to the most suitable branch for processing. This approach not only addresses the inherent limitations of conventional models in adapting to diverse driving conditions but also ensures the balance between performance and efficiency. Extensive experimental evaluations demonstrating the adaptability of DyRoNet to diverse branch selection strategies, resulting in significant performance enhancements across different scenarios. This work not only establishes a new benchmark for streaming perception but also provides valuable engineering insights for future work., Comment: Project: https://tastevision.github.io/DyRoNet/

In this paper, we abstract the process of people hearing speech, extracting meaningful cues, and creating various dynamically audio-consistent talking faces, termed Listening and Imagining, into the task of high-fidelity diverse talking faces generation from a single audio. Specifically, it involves two critical challenges: one is to effectively decouple identity, content, and emotion from entangled audio, and the other is to maintain intra-video diversity and inter-video consistency. To tackle the issues, we first dig out the intricate relationships among facial factors and simplify the decoupling process, tailoring a Progressive Audio Disentanglement for accurate facial geometry and semantics learning, where each stage incorporates a customized training module responsible for a specific factor. Secondly, to achieve visually diverse and audio-synchronized animation solely from input audio within a single model, we introduce the Controllable Coherent Frame generation, which involves the flexible integration of three trainable adapters with frozen Latent Diffusion Models (LDMs) to focus on maintaining facial geometry and semantics, as well as texture and temporal coherence between frames. In this way, we inherit high-quality diverse generation from LDMs while significantly improving their controllability at a low training cost. Extensive experiments demonstrate the flexibility and effectiveness of our method in handling this paradigm. The codes will be released at https://github.com/modelscope/facechain.

Fractional quantum Hall (FQH) states, known for their robust topological order and the emergence of non-Abelian anyons, have captured significant interest due to the appealing applications in fault-tolerant quantum computing. Bottom-up approach on an engineered quantum platform will provide opportunities to operate FQH states without external magnetic field and enhance local and coherent manipulation of these exotic states. Here we demonstrate a lattice version of photon FQH state using a programmable on-chip platform based on photon blockade and engineering gauge fields on a novel two-dimensional circuit quantum electrodynamics (QED) system. We first observe the effective photon Lorentz force and butterfly spectrum in the artificial gauge field, a prerequisite for FQH states. After adiabatic assembly of Laughlin FQH wavefunction of 1/2 filling factor from localized photons, we observe strong density correlation and chiral topological flow among the FQH photons. We then verify the unique features of FQH states in response to external fields, including the incompressibility of generating quasiparticles and the smoking-gun signature of fractional quantum Hall conductivity. Our work represents a significant advance in the bottom-up creation and manipulation of novel strongly correlated topological quantum matter composed of photons and opens up possibilities for fault-tolerant quantum information devices., Comment: 8 pages, 6 figures

This paper introduces the WordArt Designer API, a novel framework for user-driven artistic typography synthesis utilizing Large Language Models (LLMs) on ModelScope. We address the challenge of simplifying artistic typography for non-professionals by offering a dynamic, adaptive, and computationally efficient alternative to traditional rigid templates. Our approach leverages the power of LLMs to understand and interpret user input, facilitating a more intuitive design process. We demonstrate through various case studies how users can articulate their aesthetic preferences and functional requirements, which the system then translates into unique and creative typographic designs. Our evaluations indicate significant improvements in user satisfaction, design flexibility, and creative expression over existing systems. The WordArt Designer API not only democratizes the art of typography but also opens up new possibilities for personalized digital communication and design., Comment: Spotlight Paper at the Workshop on Machine Learning for Creativity and Design, 37th Conference on Neural Information Processing Systems (NeurIPS 2023). 5 pages, 5 figures

Advances in perception modeling have significantly improved the performance of object tracking. However, the current methods for specifying the target object in the initial frame are either by 1) using a box or mask template, or by 2) providing an explicit language description. These manners are cumbersome and do not allow the tracker to have self-reasoning ability. Therefore, this work proposes a new tracking task -- Instruction Tracking, which involves providing implicit tracking instructions that require the trackers to perform tracking automatically in video frames. To achieve this, we investigate the integration of knowledge and reasoning capabilities from a Large Vision-Language Model (LVLM) for object tracking. Specifically, we propose a tracker called TrackGPT, which is capable of performing complex reasoning-based tracking. TrackGPT first uses LVLM to understand tracking instructions and condense the cues of what target to track into referring embeddings. The perception component then generates the tracking results based on the embeddings. To evaluate the performance of TrackGPT, we construct an instruction tracking benchmark called InsTrack, which contains over one thousand instruction-video pairs for instruction tuning and evaluation. Experiments show that TrackGPT achieves competitive performance on referring video object segmentation benchmarks, such as getting a new state-of the-art performance of 66.5 $\mathcal{J}\&\mathcal{F}$ on Refer-DAVIS. It also demonstrates a superior performance of instruction tracking under new evaluation protocols. The code and models are available at \href{https://github.com/jiawen-zhu/TrackGPT}{https://github.com/jiawen-zhu/TrackGPT}., Comment: 8 pages, 4 figures

The goal of Universal Cross-Domain Retrieval (UCDR) is to achieve robust performance in generalized test scenarios, wherein data may belong to strictly unknown domains and categories during training. Recently, pre-trained models with prompt tuning have shown strong generalization capabilities and attained noteworthy achievements in various downstream tasks, such as few-shot learning and video-text retrieval. However, applying them directly to UCDR may not sufficiently to handle both domain shift (i.e., adapting to unfamiliar domains) and semantic shift (i.e., transferring to unknown categories). To this end, we propose \textbf{Pro}mpting-to-\textbf{S}imulate (ProS), the first method to apply prompt tuning for UCDR. ProS employs a two-step process to simulate Content-aware Dynamic Prompts (CaDP) which can impact models to produce generalized features for UCDR. Concretely, in Prompt Units Learning stage, we introduce two Prompt Units to individually capture domain and semantic knowledge in a mask-and-align way. Then, in Context-aware Simulator Learning stage, we train a Content-aware Prompt Simulator under a simulated test scenarios to produce the corresponding CaDP. Extensive experiments conducted on three benchmark datasets show that our method achieves new state-of-the-art performance without bringing excessive parameters. Our method is publicly available at https://github.com/fangkaipeng/ProS.

Improving out-of-distribution (OOD) generalization through in-distribution (ID) adaptation is a primary goal of robust fine-tuning methods beyond the naive fine-tuning approach. However, despite decent OOD generalization performance from recent robust fine-tuning methods, OOD confidence calibration for reliable machine learning has not been fully addressed. This work proposes a robust fine-tuning method that improves both OOD accuracy and calibration error in Vision Language Models (VLMs). Firstly, we show that both types of errors have a shared upper bound consisting of two terms of ID data: 1) calibration error and 2) the smallest singular value of the input covariance matrix. Based on this insight, we design a novel framework that conducts fine-tuning with a constrained multimodal contrastive loss enforcing a larger smallest singular value, which is further aided by the self-distillation of a moving averaged model to achieve well-calibrated prediction. Starting from an empirical validation of our theoretical statements, we provide extensive experimental results on ImageNet distribution shift benchmarks that demonstrate the effectiveness of our method., Comment: Presented at the NeurIPS 2023 Workshop on Distribution Shifts (DistShift)

Multi-view or even multi-modal data is appealing yet challenging for real-world applications. Detecting anomalies in multi-view data is a prominent recent research topic. However, most of the existing methods 1) are only suitable for two views or type-specific anomalies, 2) suffer from the issue of fusion disentanglement, and 3) do not support online detection after model deployment. To address these challenges, our main ideas in this paper are three-fold: multi-view learning, disentangled representation learning, and generative model. To this end, we propose dPoE, a novel multi-view variational autoencoder model that involves (1) a Product-of-Experts (PoE) layer in tackling multi-view data, (2) a Total Correction (TC) discriminator in disentangling view-common and view-specific representations, and (3) a joint loss function in wrapping up all components. In addition, we devise theoretical information bounds to control both view-common and view-specific representations. Extensive experiments on six real-world datasets markedly demonstrate that the proposed dPoE outperforms baselines., Comment: Accepted by ACM Multimedia 2023, 10 pages, 5 tables, and 3 figures

This paper introduces "WordArt Designer", a user-driven framework for artistic typography synthesis, relying on Large Language Models (LLM). The system incorporates four key modules: the "LLM Engine", "SemTypo", "StyTypo", and "TexTypo" modules. 1) The "LLM Engine", empowered by LLM (e.g., GPT-3.5-turbo), interprets user inputs and generates actionable prompts for the other modules, thereby transforming abstract concepts into tangible designs. 2) The "SemTypo module" optimizes font designs using semantic concepts, striking a balance between artistic transformation and readability. 3) Building on the semantic layout provided by the "SemTypo module", the "StyTypo module" creates smooth, refined images. 4) The "TexTypo module" further enhances the design's aesthetics through texture rendering, enabling the generation of inventive textured fonts. Notably, "WordArt Designer" highlights the fusion of generative AI with artistic typography. Experience its capabilities on ModelScope: https://www.modelscope.cn/studios/WordArt/WordArt., Comment: Accepted to EMNLP 2023, 10 pages, 11 figures, 1 table, the system is at https://www.modelscope.cn/studios/WordArt/WordArt

Existing nighttime unmanned aerial vehicle (UAV) trackers follow an "Enhance-then-Track" architecture - first using a light enhancer to brighten the nighttime video, then employing a daytime tracker to locate the object. This separate enhancement and tracking fails to build an end-to-end trainable vision system. To address this, we propose a novel architecture called Darkness Clue-Prompted Tracking (DCPT) that achieves robust UAV tracking at night by efficiently learning to generate darkness clue prompts. Without a separate enhancer, DCPT directly encodes anti-dark capabilities into prompts using a darkness clue prompter (DCP). Specifically, DCP iteratively learns emphasizing and undermining projections for darkness clues. It then injects these learned visual prompts into a daytime tracker with fixed parameters across transformer layers. Moreover, a gated feature aggregation mechanism enables adaptive fusion between prompts and between prompts and the base model. Extensive experiments show state-of-the-art performance for DCPT on multiple dark scenario benchmarks. The unified end-to-end learning of enhancement and tracking in DCPT enables a more trainable system. The darkness clue prompting efficiently injects anti-dark knowledge without extra modules. Code is available at https://github.com/bearyi26/DCPT., Comment: Accepted by ICRA2024

Accurately estimating the 3D pose of humans in video sequences requires both accuracy and a well-structured architecture. With the success of transformers, we introduce the Refined Temporal Pyramidal Compression-and-Amplification (RTPCA) transformer. Exploiting the temporal dimension, RTPCA extends intra-block temporal modeling via its Temporal Pyramidal Compression-and-Amplification (TPCA) structure and refines inter-block feature interaction with a Cross-Layer Refinement (XLR) module. In particular, TPCA block exploits a temporal pyramid paradigm, reinforcing key and value representation capabilities and seamlessly extracting spatial semantics from motion sequences. We stitch these TPCA blocks with XLR that promotes rich semantic representation through continuous interaction of queries, keys, and values. This strategy embodies early-stage information with current flows, addressing typical deficits in detail and stability seen in other transformer-based methods. We demonstrate the effectiveness of RTPCA by achieving state-of-the-art results on Human3.6M, HumanEva-I, and MPI-INF-3DHP benchmarks with minimal computational overhead. The source code is available at https://github.com/hbing-l/RTPCA., Comment: 11 pages, 5 figures

Existing 3D human pose estimators face challenges in adapting to new datasets due to the lack of 2D-3D pose pairs in training sets. To overcome this issue, we propose \textit{Multi-Hypothesis \textbf{P}ose \textbf{Syn}thesis \textbf{D}omain \textbf{A}daptation} (\textbf{PoSynDA}) framework to bridge this data disparity gap in target domain. Typically, PoSynDA uses a diffusion-inspired structure to simulate 3D pose distribution in the target domain. By incorporating a multi-hypothesis network, PoSynDA generates diverse pose hypotheses and aligns them with the target domain. To do this, it first utilizes target-specific source augmentation to obtain the target domain distribution data from the source domain by decoupling the scale and position parameters. The process is then further refined through the teacher-student paradigm and low-rank adaptation. With extensive comparison of benchmarks such as Human3.6M and MPI-INF-3DHP, PoSynDA demonstrates competitive performance, even comparable to the target-trained MixSTE model\cite{zhang2022mixste}. This work paves the way for the practical application of 3D human pose estimation in unseen domains. The code is available at https://github.com/hbing-l/PoSynDA., Comment: Accepted to ACM Multimedia 2023; 10 pages, 4 figures, 8 tables; the code is at https://github.com/hbing-l/PoSynDA

Anomaly segmentation plays a pivotal role in identifying atypical objects in images, crucial for hazard detection in autonomous driving systems. While existing methods demonstrate noteworthy results on synthetic data, they often fail to consider the disparity between synthetic and real-world data domains. Addressing this gap, we introduce the Multi-Granularity Cross-Domain Alignment (MGCDA) framework, tailored to harmonize features across domains at both the scene and individual sample levels. Our contributions are twofold: i) We present the Multi-source Domain Adversarial Training module. This integrates a multi-source adversarial loss coupled with dynamic label smoothing, facilitating the learning of domain-agnostic representations across multiple processing stages. ii) We propose an innovative Cross-domain Anomaly-aware Contrastive Learning methodology.} This method adeptly selects challenging anchor points and images using an anomaly-centric strategy, ensuring precise alignment at the sample level. Extensive evaluations of the Fishyscapes and RoadAnomaly datasets demonstrate MGCDA's superior performance and adaptability. Additionally, its ability to perform parameter-free inference and function with various network architectures highlights its distinctiveness in advancing the frontier of anomaly segmentation., Comment: Accepted to ACM Multimedia 2023

Quantum key distribution (QKD) can provide fundamentally proven security for secure communication. Toward application, the secret key rate (SKR) is a key figure of merit for any QKD system. So far, the SKR has been limited to about a few megabit-per-second. Here we report a QKD system that is able to generate key at a record high SKR of 115.8 Mb/s over 10-km standard fibre, and to distribute key over up to 328 km of ultra-low-loss fibre. This attributes to a multi-pixel superconducting nanowire single-photon detector with ultrahigh counting rate, an integrated transmitter that can stably encode polarization states with low error, a fast post-processing algorithm for generating key in real time and the high system clock-rate operation. The results demonstrate the feasibility of practical high-rate QKD with photonic techniques, thus opening its possibility for widespread applications.

The Hong-Ou-Mandel interference between independent photons plays a pivotal role in the large-scale quantum networks involving distant nodes. Photons need to work in a pure state for indistinguishability to reach high-quality interference. Also, they need to have a sufficiently long coherence time to reduce the time synchronization requirements in practical application. In this paper, we discuss a scheme for generating a pure-state photon-pair source with a long coherence time in periodically poled potassium titanyl phosphate (PPKTP) crystals. By selecting the appropriate pump laser and filter, we could simultaneously eliminate the frequency correlation of the parametric photons while achieving a long coherence time. We experimentally developed this pure-state photon-pair source of 780 nm on PPKTP crystals pumped by a 390 nm pulsed laser. The source provided a coherence time of tens of picoseconds, and it showed to have the potential to be applied in long-distance quantum interference. Furthermore, we experimentally demonstrated the Hong-Ou-Mandel (HOM) interference between two photon sources with visibility exceeding the classical limit.

Fault-tolerant quantum computing based on surface code has emerged as an attractive candidate for practical large-scale quantum computers to achieve robust noise resistance. To achieve universality, magic states preparation is a commonly approach for introducing non-Clifford gates. Here, we present a hardware-efficient and scalable protocol for arbitrary logical state preparation for the rotated surface code, and further experimentally implement it on the \textit{Zuchongzhi} 2.1 superconducting quantum processor. An average of \hhl{$0.8983 \pm 0.0002$} logical fidelity at different logical states with distance-three is achieved, \hhl{taking into account both state preparation and measurement errors.} In particular, \hhl{the magic states $|A^{\pi/4}\rangle_L$, $|H\rangle_L$, and $|T\rangle_L$ are prepared non-destructively with logical fidelities of $0.8771 \pm 0.0009 $, $0.9090 \pm 0.0009 $, and $0.8890 \pm 0.0010$, respectively, which are higher than the state distillation protocol threshold, 0.859 (for H-type magic state) and 0.827 (for T -type magic state).} Our work provides a viable and efficient avenue for generating high-fidelity raw logical magic states, which is essential for realizing non-Clifford logical gates in the surface code., Comment: In this version, we do not employ readout error mitigation strategies (in the previous version, we use readout transition matrix to mitigate the measurement error) to remove measurement errors because we believe it provides a more predictive assessment of the actual fidelity when generating and consuming magic states for a non-Clifford gate, as consuming the state involves measurement

Accurate facial landmark detection is critical for facial analysis tasks, yet prevailing heatmap and coordinate regression methods grapple with prohibitive computational costs and quantization errors. Through comprehensive theoretical analysis and experimentation, we identify and elucidate the limitations of existing techniques. To overcome these challenges, we pioneer the application of True-Range Multilateration, originally devised for GPS localization, to facial landmark detection. We propose KeyPoint Positioning System (KeyPosS) - the first framework to deduce exact landmark coordinates by triangulating distances between points of interest and anchor points predicted by a fully convolutional network. A key advantage of KeyPosS is its plug-and-play nature, enabling flexible integration into diverse decoding pipelines. Extensive experiments on four datasets demonstrate state-of-the-art performance, with KeyPosS outperforming existing methods in low-resolution settings despite minimal computational overhead. By spearheading the integration of Multilateration with facial analysis, KeyPosS marks a paradigm shift in facial landmark detection. The code is available at https://github.com/zhiqic/KeyPosS., Comment: Accepted to ACM Multimedia 2023; 10 pages, 7 figures, 6 tables; the code is at https://github.com/zhiqic/KeyPosS