Recently, digital humans for interpersonal interaction in virtual environments have gained significant attention. In this paper, we introduce a novel multi-dancer synthesis task called partner dancer generation, which involves synthesizing virtual human dancers capable of performing dance with users. The task aims to control the pose diversity between the lead dancer and the partner dancer. The core of this task is to ensure the controllable diversity of the generated partner dancer while maintaining temporal coordination with the lead dancer. This scenario varies from earlier research in generating dance motions driven by music, as our emphasis is on automatically designing partner dancer postures according to pre-defined diversity, the pose of lead dancer, as well as the accompanying tunes. To achieve this objective, we propose a three-stage framework called Dance-with-You (DanY). Initially, we employ a 3D Pose Collection stage to collect a wide range of basic dance poses as references for motion generation. Then, we introduce a hyper-parameter that coordinates the similarity between dancers by masking poses to prevent the generation of sequences that are over-diverse or consistent. To avoid the rigidity of movements, we design a Dance Pre-generated stage to pre-generate these masked poses instead of filling them with zeros. After that, a Dance Motion Transfer stage is adopted with leader sequences and music, in which a multi-conditional sampling formula is rewritten to transfer the pre-generated poses into a sequence with a partner style. In practice, to address the lack of multi-person datasets, we introduce AIST-M, a new dataset for partner dancer generation, which is publicly availiable. Comprehensive evaluations on our AIST-M dataset demonstrate that the proposed DanY can synthesize satisfactory partner dancer results with controllable diversity.
相關內容
Analogy-making between narratives is one of the most critical abilities in natural language understanding. In this paper, we evaluate the ability to identify and generate analogy by building a first-of-its-kind large-scale story-level analogy corpus, StoryAnalogy, which contains 24K story pairs from diverse domains with human annotations on two similarities from the extended Structure-Mapping Theory. We design a set of tests on StoryAnalogy, presenting the first evaluation of story-level analogy identification and generation. Interestingly, we find that the analogy identification tasks are extremely challenging not only for the sentence embedding models but also for the recent large language models (LLMs) such as ChatGPT and LLaMa, where ChatGPT only achieved around 30% accuracy in multiple-choice questions (> 85% accuracy for humans). Finally, we find that data in StoryAnalogy can improve LLMs analogy generation quality, where a fine-tuned FlanT5-xxl model yields comparable performance to zero-shot ChatGPT.
In many real-world scenarios (e.g., academic networks, social platforms), different types of entities are not only associated with texts but also connected by various relationships, which can be abstracted as Text-Attributed Heterogeneous Graphs (TAHGs). Current pretraining tasks for Language Models (LMs) primarily focus on separately learning the textual information of each entity and overlook the crucial aspect of capturing topological connections among entities in TAHGs. In this paper, we present a new pretraining framework for LMs that explicitly considers the topological and heterogeneous information in TAHGs. Firstly, we define a context graph as neighborhoods of a target node within specific orders and propose a topology-aware pretraining task to predict nodes involved in the context graph by jointly optimizing an LM and an auxiliary heterogeneous graph neural network. Secondly, based on the observation that some nodes are text-rich while others have little text, we devise a text augmentation strategy to enrich textless nodes with their neighbors' texts for handling the imbalance issue. We conduct link prediction and node classification tasks on three datasets from various domains. Experimental results demonstrate the superiority of our approach over existing methods and the rationality of each design. Our code is available at //github.com/Hope-Rita/THLM.
Physical human-robot interactions (pHRIs) can improve robot autonomy and reduce physical demands on humans. In this paper, we consider a collaborative task with a considerably long object and no prior knowledge of the object's parameters. An integrated control framework with an online object parameter estimator and a Cartesian object-aware impedance controller is proposed to realize complicated scenarios. During the transportation task, the object parameters are estimated online while a robot and human lift an object. The perturbation motion is incorporated into the null space of the desired trajectory to enhance the estimator accuracy. An object-aware impedance controller is designed using the real-time estimation results to effectively transmit the intended human motion to the robot through the object. Experimental demonstrations of collaborative tasks, including object transportation and assembly tasks, are implemented to show the effectiveness of our proposed method.
In this paper, we propose a novel method for 3D scene and object reconstruction from sparse multi-view images. Different from previous methods that leverage extra information such as depth or generalizable features across scenes, our approach leverages the scene properties embedded in the multi-view inputs to create precise pseudo-labels for optimization without any prior training. Specifically, we introduce a geometry-guided approach that improves surface reconstruction accuracy from sparse views by leveraging spherical harmonics to predict the novel radiance while holistically considering all color observations for a point in the scene. Also, our pipeline exploits proxy geometry and correctly handles the occlusion in generating the pseudo-labels of radiance, which previous image-warping methods fail to avoid. Our method, dubbed Ray Augmentation (RayAug), achieves superior results on DTU and Blender datasets without requiring prior training, demonstrating its effectiveness in addressing the problem of sparse view reconstruction. Our pipeline is flexible and can be integrated into other implicit neural reconstruction methods for sparse views.
An experimental Quantum Key Distribution (QKD) implementation requires advanced costly hardware, unavailable in most research environments, making protocol testing and performance evaluation complicated. Historically, this has been a major motivation for the development of QKD simulation frameworks, to allow researchers to obtain insight before proceeding into practical implementations. Several simulators have been introduced over the recent years. However, only four are publicly available, only one of which models equipment imperfections. Currently, no open-source simulator includes all following capabilities: channel attenuation modelling, equipment imperfections and effect on key rates, estimation of elapsed time during quantum channel processes, use of truly random binary sequences for qubits and measurement bases, shared-bit fraction customization. In this paper, we present NuQKD, an open-source modular, intuitive simulator, featuring all the above capabilities. NuQKD establishes communication between two computer terminals, accepts custom inputs (iterations, raw key size, interception rate etc.) and evaluates the sifted key length, Quantum Bit Error Rate (QBER), elapsed communication time and more). NuQKD capabilities include optical fiber and free-space simulation, modeling of equipment/channel imperfections, bitstrings from True Random Number Generator, modular design and automated evaluation of performance metrics. We expect NuQKD to enable convenient and accurate representation of actual experimental conditions.
This paper targets high-fidelity and real-time view synthesis of dynamic 3D scenes at 4K resolution. Recently, some methods on dynamic view synthesis have shown impressive rendering quality. However, their speed is still limited when rendering high-resolution images. To overcome this problem, we propose 4K4D, a 4D point cloud representation that supports hardware rasterization and enables unprecedented rendering speed. Our representation is built on a 4D feature grid so that the points are naturally regularized and can be robustly optimized. In addition, we design a novel hybrid appearance model that significantly boosts the rendering quality while preserving efficiency. Moreover, we develop a differentiable depth peeling algorithm to effectively learn the proposed model from RGB videos. Experiments show that our representation can be rendered at over 400 FPS on the DNA-Rendering dataset at 1080p resolution and 80 FPS on the ENeRF-Outdoor dataset at 4K resolution using an RTX 4090 GPU, which is 30x faster than previous methods and achieves the state-of-the-art rendering quality. Our project page is available at //zju3dv.github.io/4k4d/.
Extracting structured information from videos is critical for numerous downstream applications in the industry. In this paper, we define a significant task of extracting hierarchical key information from visual texts on videos. To fulfill this task, we decouples it into four subtasks and introduce two implementation solutions called PipVKIE and UniVKIE. PipVKIE sequentially completes the four subtasks in continuous stages, while UniVKIE is improved by unifying all the subtasks into one backbone. Both PipVKIE and UniVKIE leverage multimodal information from vision, text, and coordinates for feature representation. Extensive experiments on one well-defined dataset demonstrate that our solutions can achieve remarkable performance and efficient inference speed. The code and dataset will be publicly available.
This paper introduces a new benchmark dataset, Open-Structure, for evaluating visual odometry and SLAM methods, which directly equips point and line measurements, correspondences, structural associations, and co-visibility factor graphs instead of providing raw images. Based on the proposed benchmark dataset, these 2D or 3D data can be directly input to different stages of SLAM pipelines to avoid the impact of the data preprocessing modules in ablation experiments. First, we propose a dataset generator for real-world and simulated scenarios. In real-world scenes, it maintains the same observations and occlusions as actual feature extraction results. Those generated simulation sequences enhance the dataset's diversity by introducing various carefully designed trajectories and observations. Second, a SLAM baseline is proposed using our dataset to evaluate widely used modules in camera pose tracking, parametrization, and optimization modules. By evaluating these state-of-the-art algorithms across different scenarios, we discern each module's strengths and weaknesses within the camera tracking and optimization process. Our dataset and baseline are available at \url{//github.com/yanyan-li/Open-Structure}.
Transformer is a promising neural network learner, and has achieved great success in various machine learning tasks. Thanks to the recent prevalence of multimodal applications and big data, Transformer-based multimodal learning has become a hot topic in AI research. This paper presents a comprehensive survey of Transformer techniques oriented at multimodal data. The main contents of this survey include: (1) a background of multimodal learning, Transformer ecosystem, and the multimodal big data era, (2) a theoretical review of Vanilla Transformer, Vision Transformer, and multimodal Transformers, from a geometrically topological perspective, (3) a review of multimodal Transformer applications, via two important paradigms, i.e., for multimodal pretraining and for specific multimodal tasks, (4) a summary of the common challenges and designs shared by the multimodal Transformer models and applications, and (5) a discussion of open problems and potential research directions for the community.
In this paper we address issues with image retrieval benchmarking on standard and popular Oxford 5k and Paris 6k datasets. In particular, annotation errors, the size of the dataset, and the level of challenge are addressed: new annotation for both datasets is created with an extra attention to the reliability of the ground truth. Three new protocols of varying difficulty are introduced. The protocols allow fair comparison between different methods, including those using a dataset pre-processing stage. For each dataset, 15 new challenging queries are introduced. Finally, a new set of 1M hard, semi-automatically cleaned distractors is selected. An extensive comparison of the state-of-the-art methods is performed on the new benchmark. Different types of methods are evaluated, ranging from local-feature-based to modern CNN based methods. The best results are achieved by taking the best of the two worlds. Most importantly, image retrieval appears far from being solved.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191