Current state-of-the-art (SOTA) methods in 3D Human Pose Estimation (HPE) are primarily based on Transformers. However, existing Transformer-based 3D HPE backbones often encounter a trade-off between accuracy and computational efficiency. To resolve the above dilemma, in this work, leveraging recent advances in state space models, we utilize Mamba for high-quality and efficient long-range modeling. Nonetheless, Mamba still faces challenges in precisely exploiting the local dependencies between joints. To address these issues, we propose a new attention-free hybrid spatiotemporal architecture named Hybrid Mamba-GCN (Pose Magic). This architecture introduces local enhancement with GCN by capturing relationships between neighboring joints, thus producing new representations to complement Mamba's outputs. By adaptively fusing representations from Mamba and GCN, Pose Magic demonstrates superior capability in learning the underlying 3D structure. To meet the requirements of real-time inference, we also provide a fully causal version. Extensive experiments show that Pose Magic achieves new SOTA results ($\downarrow 0.9 mm$) while saving $74.1\%$ FLOPs. In addition, Pose Magic exhibits optimal motion consistency and the ability to generalize to unseen sequence lengths.
相關內容
Despite the recent advancements in Large Language Models (LLMs), which have significantly enhanced the generative capabilities for various NLP tasks, LLMs still face limitations in directly handling retrieval tasks. However, many practical applications demand the seamless integration of both retrieval and generation. This paper introduces a novel and efficient One-pass Generation and retrieval framework (OneGen), designed to improve LLMs' performance on tasks that require both generation and retrieval. The proposed framework bridges the traditionally separate training approaches for generation and retrieval by incorporating retrieval tokens generated autoregressively. This enables a single LLM to handle both tasks simultaneously in a unified forward pass. We conduct experiments on two distinct types of composite tasks, RAG and Entity Linking, to validate the pluggability, effectiveness, and efficiency of OneGen in training and inference. Furthermore, our results show that integrating generation and retrieval within the same context preserves the generative capabilities of LLMs while improving retrieval performance. To the best of our knowledge, OneGen is the first to enable LLMs to conduct vector retrieval during the generation.
Convolutional Neural Networks (CNNs) and Transformers have achieved remarkable success in computer vision tasks. However, their deep architectures often lead to high computational redundancy, making them less suitable for resource-constrained environments, such as edge devices. This paper introduces ParFormer, a novel vision transformer that addresses this challenge by incorporating a Parallel Mixer and a Sparse Channel Attention Patch Embedding (SCAPE). By combining convolutional and attention mechanisms, ParFormer improves feature extraction. This makes spatial feature extraction more efficient and cuts down on unnecessary computation. The SCAPE module further reduces computational redundancy while preserving essential feature information during down-sampling. Experimental results on the ImageNet-1K dataset show that ParFormer-T achieves 78.9\% Top-1 accuracy with a high throughput on a GPU that outperforms other small models with 2.56$\times$ higher throughput than MobileViT-S, 0.24\% faster than FasterNet-T2, and 1.79$\times$ higher than EdgeNeXt-S. For edge device deployment, ParFormer-T excels with a throughput of 278.1 images/sec, which is 1.38 $\times$ higher than EdgeNeXt-S and 2.36$\times$ higher than MobileViT-S, making it highly suitable for real-time applications in resource-constrained settings. The larger variant, ParFormer-L, reaches 83.5\% Top-1 accuracy, offering a balanced trade-off between accuracy and efficiency, surpassing many state-of-the-art models. In COCO object detection, ParFormer-M achieves 40.7 AP for object detection and 37.6 AP for instance segmentation, surpassing models like ResNet-50, PVT-S and PoolFormer-S24 with significantly higher efficiency. These results validate ParFormer as a highly efficient and scalable model for both high-performance and resource-constrained scenarios, making it an ideal solution for edge-based AI applications.
Neural Radiance Field (NeRF) has been proposed as an innovative advancement in 3D reconstruction techniques. However, little research has been conducted on the issues of information confidentiality and security to NeRF, such as steganography. Existing NeRF steganography solutions have shortcomings in low steganography quality, model weight damage, and limited amount of steganographic information. This paper proposes Noise-NeRF, a novel NeRF steganography method employing Adaptive Pixel Selection strategy and Pixel Perturbation strategy to improve the quality and efficiency of steganography via trainable noise. Extensive experiments validate the state-of-the-art performances of Noise-NeRF on both steganography quality and rendering quality, as well as effectiveness in super-resolution image steganography.
Large Vision-Language Models (LVLMs) have shown remarkable performance on many visual-language tasks. However, these models still suffer from multimodal hallucination, which means the generation of objects or content that violates the images. Many existing work detects hallucination by directly judging whether an object exists in an image, overlooking the association between the object and semantics. To address this issue, we propose Hierarchical Feedback Learning with Vision-enhanced Penalty Decoding (HELPD). This framework incorporates hallucination feedback at both object and sentence semantic levels. Remarkably, even with a marginal degree of training, this approach can alleviate over 15% of hallucination. Simultaneously, HELPD penalizes the output logits according to the image attention window to avoid being overly affected by generated text. HELPD can be seamlessly integrated with any LVLMs. Our experiments demonstrate that the proposed framework yields favorable results across multiple hallucination benchmarks. It effectively mitigates hallucination for different LVLMs and concurrently improves their text generation quality.
To address the occlusion issues in person Re-Identification (ReID) tasks, many methods have been proposed to extract part features by introducing external spatial information. However, due to missing part appearance information caused by occlusion and noisy spatial information from external model, these purely vision-based approaches fail to correctly learn the features of human body parts from limited training data and struggle in accurately locating body parts, ultimately leading to misaligned part features. To tackle these challenges, we propose a Prompt-guided Feature Disentangling method (ProFD), which leverages the rich pre-trained knowledge in the textual modality facilitate model to generate well-aligned part features. ProFD first designs part-specific prompts and utilizes noisy segmentation mask to preliminarily align visual and textual embedding, enabling the textual prompts to have spatial awareness. Furthermore, to alleviate the noise from external masks, ProFD adopts a hybrid-attention decoder, ensuring spatial and semantic consistency during the decoding process to minimize noise impact. Additionally, to avoid catastrophic forgetting, we employ a self-distillation strategy, retaining pre-trained knowledge of CLIP to mitigate over-fitting. Evaluation results on the Market1501, DukeMTMC-ReID, Occluded-Duke, Occluded-ReID, and P-DukeMTMC datasets demonstrate that ProFD achieves state-of-the-art results. Our project is available at: //github.com/Cuixxx/ProFD.
This research aims to evaluate the performance of several Recurrent Neural Network (RNN) architectures including Simple RNN, Gated Recurrent Units (GRU), and Long Short-Term Memory (LSTM), compared to classic algorithms such as Random Forest and XGBoost in building classification models for early crash detection in ASEAN-5 stock markets. The study is examined using imbalanced data, which is common due to the rarity of market crashes. The study analyzes daily data from 2010 to 2023 across the major stock markets of the ASEAN-5 countries, including Indonesia, Malaysia, Singapore, Thailand, and Philippines. Market crash is identified as the target variable when the major stock price indices fall below the Value at Risk (VaR) thresholds of 5%, 2.5% and 1%. predictors involving technical indicators of major local and global markets as well as commodity markets. This study includes 213 predictors with their respective lags (5, 10, 15, 22, 50, 200) and uses a time step of 7, expanding the total number of predictors to 1491. The challenge of data imbalance is addressed with SMOTE-ENN. The results show that all RNN-Based architectures outperform Random Forest and XGBoost. Among the various RNN architectures, Simple RNN stands out as the most superior, mainly due to the data characteristics that are not overly complex and focus more on short-term information. This study enhances and extends the range of phenomena observed in previous studies by incorporating variables like different geographical zones and time periods, as well as methodological adjustments.
Even in recent neural network architectures such as Transformers and Extended LSTM (xLSTM), and traditional ones like Convolutional Neural Networks, Activation Functions are an integral part of nearly all neural networks. They enable more effective training and capture nonlinear data patterns. More than 400 functions have been proposed over the last 30 years, including fixed or trainable parameters, but only a few are widely used. ReLU is one of the most frequently used, with GELU and Swish variants increasingly appearing. However, ReLU presents non-differentiable points and exploding gradient issues, while testing different parameters of GELU and Swish variants produces varying results, needing more parameters to adapt to datasets and architectures. This article introduces a novel set of activation functions called Zorro, a continuously differentiable and flexible family comprising five main functions fusing ReLU and Sigmoid. Zorro functions are smooth and adaptable, and serve as information gates, aligning with ReLU in the 0-1 range, offering an alternative to ReLU without the need for normalization, neuron death, or gradient explosions. Zorro also approximates functions like Swish, GELU, and DGELU, providing parameters to adjust to different datasets and architectures. We tested it on fully connected, convolutional, and transformer architectures to demonstrate its effectiveness.
With the bomb ignited by ChatGPT, Transformer-based Large Language Models (LLMs) have paved a revolutionary path toward Artificial General Intelligence (AGI) and have been applied in diverse areas as knowledge bases, human interfaces, and dynamic agents. However, a prevailing limitation exists: many current LLMs, constrained by resources, are primarily pre-trained on shorter texts, rendering them less effective for longer-context prompts, commonly encountered in real-world settings. In this paper, we present a comprehensive survey focusing on the advancement of model architecture in Transformer-based LLMs to optimize long-context capabilities across all stages from pre-training to inference. We firstly delineate and analyze the problems of handling long-context input and output with the current Transformer-based models. Then, we mainly offer a holistic taxonomy to navigate the landscape of Transformer upgrades on architecture to solve these problems. Afterward, we provide the investigation on wildly used evaluation necessities tailored for long-context LLMs, including datasets, metrics, and baseline models, as well as some amazing optimization toolkits like libraries, systems, and compilers to augment LLMs' efficiency and efficacy across different stages. Finally, we further discuss the predominant challenges and potential avenues for future research in this domain. Additionally, we have established a repository where we curate relevant literature with real-time updates at //github.com/Strivin0311/long-llms-learning.
Graph Neural Networks (GNNs) have gained momentum in graph representation learning and boosted the state of the art in a variety of areas, such as data mining (\emph{e.g.,} social network analysis and recommender systems), computer vision (\emph{e.g.,} object detection and point cloud learning), and natural language processing (\emph{e.g.,} relation extraction and sequence learning), to name a few. With the emergence of Transformers in natural language processing and computer vision, graph Transformers embed a graph structure into the Transformer architecture to overcome the limitations of local neighborhood aggregation while avoiding strict structural inductive biases. In this paper, we present a comprehensive review of GNNs and graph Transformers in computer vision from a task-oriented perspective. Specifically, we divide their applications in computer vision into five categories according to the modality of input data, \emph{i.e.,} 2D natural images, videos, 3D data, vision + language, and medical images. In each category, we further divide the applications according to a set of vision tasks. Such a task-oriented taxonomy allows us to examine how each task is tackled by different GNN-based approaches and how well these approaches perform. Based on the necessary preliminaries, we provide the definitions and challenges of the tasks, in-depth coverage of the representative approaches, as well as discussions regarding insights, limitations, and future directions.
UniViLM: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation
We propose UniViLM: a Unified Video and Language pre-training Model for multimodal understanding and generation. Motivated by the recent success of BERT based pre-training technique for NLP and image-language tasks, VideoBERT and CBT are proposed to exploit BERT model for video and language pre-training using narrated instructional videos. Different from their works which only pre-train understanding task, we propose a unified video-language pre-training model for both understanding and generation tasks. Our model comprises of 4 components including two single-modal encoders, a cross encoder and a decoder with the Transformer backbone. We first pre-train our model to learn the universal representation for both video and language on a large instructional video dataset. Then we fine-tune the model on two multimodal tasks including understanding task (text-based video retrieval) and generation task (multimodal video captioning). Our extensive experiments show that our method can improve the performance of both understanding and generation tasks and achieves the state-of-the art results.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191