Existing music-driven 3D dance generation methods mainly concentrate on high-quality dance generation, but lack sufficient control during the generation process. To address these issues, we propose a unified framework capable of generating high-quality dance movements and supporting multi-modal control, including genre control, semantic control, and spatial control. First, we decouple the dance generation network from the dance control network, thereby avoiding the degradation in dance quality when adding additional control information. Second, we design specific control strategies for different control information and integrate them into a unified framework. Experimental results show that the proposed dance generation framework outperforms state-of-the-art methods in terms of motion quality and controllability.
Recent advancements in Text-to-SQL methods employing Large Language Models (LLMs) have demonstrated remarkable performance. Nonetheless, these approaches continue to encounter difficulties when handling extensive databases, intricate user queries, and erroneous SQL results. To tackle these challenges, we present \textsc{MAC-SQL}, a novel LLM-based multi-agent collaborative framework designed for the Text-to-SQL task. Our framework comprises three agents: the \textit{Selector}, accountable for condensing voluminous databases and preserving relevant table schemas for user questions; the \textit{Decomposer}, which disassembles complex user questions into more straightforward sub-problems and resolves them progressively; and the \textit{Refiner}, tasked with validating and refining defective SQL queries. We perform comprehensive experiments on two Text-to-SQL datasets, BIRD and Spider, achieving a state-of-the-art execution accuracy of 59.59\% on the BIRD test set. Moreover, we have open-sourced an instruction fine-tuning model, SQL-Llama, based on Code Llama 7B, in addition to an agent instruction dataset derived from training data based on BIRD and Spider. The SQL-Llama model has demonstrated encouraging results on the development sets of both BIRD and Spider. However, when compared to GPT-4, there remains a notable potential for enhancement. Our code and data are publicly available at https://github.com/wbbeyourself/MAC-SQL.
High-resolution representation is essential for achieving good performance in human pose estimation models. To obtain such features, existing works utilize high-resolution input images or fine-grained image tokens. However, this dense high-resolution representation brings a significant computational burden. In this paper, we address the following question: "Only sparse human keypoint locations are detected for human pose estimation, is it really necessary to describe the whole image in a dense, high-resolution manner?" Based on dynamic transformer models, we propose a framework that only uses Sparse High-resolution Representations for human Pose estimation (SHaRPose). In detail, SHaRPose consists of two stages. At the coarse stage, the relations between image regions and keypoints are dynamically mined while a coarse estimation is generated. Then, a quality predictor is applied to decide whether the coarse estimation results should be refined. At the fine stage, SHaRPose builds sparse high-resolution representations only on the regions related to the keypoints and provides refined high-precision human pose estimations. Extensive experiments demonstrate the outstanding performance of the proposed method. Specifically, compared to the state-of-the-art method ViTPose, our model SHaRPose-Base achieves 77.4 AP (+0.5 AP) on the COCO validation set and 76.7 AP (+0.5 AP) on the COCO test-dev set, and infers at a speed of $1.4\times$ faster than ViTPose-Base.
One of the key components within diffusion models is the UNet for noise prediction. While several works have explored basic properties of the UNet decoder, its encoder largely remains unexplored. In this work, we conduct the first comprehensive study of the UNet encoder. We empirically analyze the encoder features and provide insights to important questions regarding their changes at the inference process. In particular, we find that encoder features change gently, whereas the decoder features exhibit substantial variations across different time-steps. This finding inspired us to omit the encoder at certain adjacent time-steps and reuse cyclically the encoder features in the previous time-steps for the decoder. Further based on this observation, we introduce a simple yet effective encoder propagation scheme to accelerate the diffusion sampling for a diverse set of tasks. By benefiting from our propagation scheme, we are able to perform in parallel the decoder at certain adjacent time-steps. Additionally, we introduce a prior noise injection method to improve the texture details in the generated image. Besides the standard text-to-image task, we also validate our approach on other tasks: text-to-video, personalized generation and reference-guided generation. Without utilizing any knowledge distillation technique, our approach accelerates both the Stable Diffusion (SD) and the DeepFloyd-IF models sampling by 41$\%$ and 24$\%$ respectively, while maintaining high-quality generation performance. Our code is available in \href{https://github.com/hutaiHang/Faster-Diffusion}{FasterDiffusion}.
Depth super-resolution (DSR) aims to restore high-resolution (HR) depth from low-resolution (LR) one, where RGB image is often used to promote this task. Recent image guided DSR approaches mainly focus on spatial domain to rebuild depth structure. However, since the structure of LR depth is usually blurry, only considering spatial domain is not very sufficient to acquire satisfactory results. In this paper, we propose structure guided network (SGNet), a method that pays more attention to gradient and frequency domains, both of which have the inherent ability to capture high-frequency structure. Specifically, we first introduce the gradient calibration module (GCM), which employs the accurate gradient prior of RGB to sharpen the LR depth structure. Then we present the Frequency Awareness Module (FAM) that recursively conducts multiple spectrum differencing blocks (SDB), each of which propagates the precise high-frequency components of RGB into the LR depth. Extensive experimental results on both real and synthetic datasets demonstrate the superiority of our SGNet, reaching the state-of-the-art. Codes and pre-trained models are available at https://github.com/yanzq95/SGNet.
Large-scale pre-training has proven to be an effective method for improving performance across different tasks. Current person search methods use ImageNet pre-trained models for feature extraction, yet it is not an optimal solution due to the gap between the pre-training task and person search task (as a downstream task). Therefore, in this paper, we focus on pre-training for person search, which involves detecting and re-identifying individuals simultaneously. Although labeled data for person search is scarce, datasets for two sub-tasks person detection and re-identification are relatively abundant. To this end, we propose a hybrid pre-training framework specifically designed for person search using sub-task data only. It consists of a hybrid learning paradigm that handles data with different kinds of supervisions, and an intra-task alignment module that alleviates domain discrepancy under limited resources. To the best of our knowledge, this is the first work that investigates how to support full-task pre-training using sub-task data. Extensive experiments demonstrate that our pre-trained model can achieve significant improvements across diverse protocols, such as person search method, fine-tuning data, pre-training data and model backbone. For example, our model improves ResNet50 based NAE by 10.3% relative improvement w.r.t. mAP. Our code and pre-trained models are released for plug-and-play usage to the person search community.
In this paper, we introduce an SE(3) diffusion model-based point cloud registration framework for 6D object pose estimation in real-world scenarios. Our approach formulates the 3D registration task as a denoising diffusion process, which progressively refines the pose of the source point cloud to obtain a precise alignment with the model point cloud. Training our framework involves two operations: An SE(3) diffusion process and an SE(3) reverse process. The SE(3) diffusion process gradually perturbs the optimal rigid transformation of a pair of point clouds by continuously injecting noise (perturbation transformation). By contrast, the SE(3) reverse process focuses on learning a denoising network that refines the noisy transformation step-by-step, bringing it closer to the optimal transformation for accurate pose estimation. Unlike standard diffusion models used in linear Euclidean spaces, our diffusion model operates on the SE(3) manifold. This requires exploiting the linear Lie algebra $\mathfrak{se}(3)$ associated with SE(3) to constrain the transformation transitions during the diffusion and reverse processes. Additionally, to effectively train our denoising network, we derive a registration-specific variational lower bound as the optimization objective for model learning. Furthermore, we show that our denoising network can be constructed with a surrogate registration model, making our approach applicable to different deep registration networks. Extensive experiments demonstrate that our diffusion registration framework presents outstanding pose estimation performance on the real-world TUD-L, LINEMOD, and Occluded-LINEMOD datasets.
Multimodal manga analysis focuses on enhancing manga understanding with visual and textual features, which has attracted considerable attention from both natural language processing and computer vision communities. Currently, most comics are hand-drawn and prone to problems such as missing pages, text contamination, and aging, resulting in missing comic text content and seriously hindering human comprehension. In other words, the Multimodal Manga Complement (M2C) task has not been investigated, which aims to handle the aforementioned issues by providing a shared semantic space for vision and language understanding. To this end, we first propose the Multimodal Manga Complement task by establishing a new M2C benchmark dataset covering two languages. First, we design a manga argumentation method called MCoT to mine event knowledge in comics with large language models. Then, an effective baseline FVP-M$^{2}$ using fine-grained visual prompts is proposed to support manga complement. Extensive experimental results show the effectiveness of FVP-M$^{2}$ method for Multimodal Mange Complement.
Cascade ranking is widely used for large-scale top-k selection problems in online advertising and recommendation systems, and learning-to-rank is an important way to optimize the models in cascade ranking systems. Previous works on learning-to-rank usually focus on letting the model learn the complete order or pay more attention to the order of top materials, and adopt the corresponding rank metrics as optimization targets. However, these optimization targets can not adapt to various cascade ranking scenarios with varying data complexities and model capabilities; and the existing metric-driven methods such as the Lambda framework can only optimize a rough upper bound of the metric, potentially resulting in performance misalignment. To address these issues, we first propose a novel perspective on optimizing cascade ranking systems by highlighting the adaptability of optimization targets to data complexities and model capabilities. Concretely, we employ multi-task learning framework to adaptively combine the optimization of relaxed and full targets, which refers to metrics Recall@m@k and OAP respectively. Then we introduce a permutation matrix to represent the rank metrics and employ differentiable sorting techniques to obtain a relaxed permutation matrix with controllable approximate error bound. This enables us to optimize both the relaxed and full targets directly and more appropriately using the proposed surrogate losses within the deep learning framework. We named this method as Adaptive Neural Ranking Framework. We use the NeuralSort method to obtain the relaxed permutation matrix and draw on the uncertainty weight method in multi-task learning to optimize the proposed losses jointly. Experiments on a total of 4 public and industrial benchmarks show the effectiveness and generalization of our method, and online experiment shows that our method has significant application value.
In continual learning, the learner learns multiple tasks in sequence, with data being acquired only once for each task. Catastrophic forgetting is a major challenge to continual learning. To reduce forgetting, some existing rehearsal-based methods use episodic memory to replay samples of previous tasks. However, in the process of knowledge integration when learning a new task, this strategy also suffers from catastrophic forgetting due to an imbalance between old and new knowledge. To address this problem, we propose a novel replay strategy called Manifold Expansion Replay (MaER). We argue that expanding the implicit manifold of the knowledge representation in the episodic memory helps to improve the robustness and expressiveness of the model. To this end, we propose a greedy strategy to keep increasing the diameter of the implicit manifold represented by the knowledge in the buffer during memory management. In addition, we introduce Wasserstein distance instead of cross entropy as distillation loss to preserve previous knowledge. With extensive experimental validation on MNIST, CIFAR10, CIFAR100, and TinyImageNet, we show that the proposed method significantly improves the accuracy in continual learning setup, outperforming the state of the arts.