Related papers: SDPose: Tokenized Pose Estimation via Circulation-…

Human pose estimation has seen widespread use of transformer models in recent years. Pose transformers benefit from the self-attention map, which captures the correlation between human joint tokens and the image. However, training such…

In practical applications of human pose estimation, low-resolution inputs frequently occur, and existing state-of-the-art models perform poorly with low-resolution images. This work focuses on boosting the performance of low-resolution…

The landscape of high-performance image generation models is currently shifting from the inefficient multi-step ones to the efficient few-step counterparts (e.g, Z-Image-Turbo and FLUX.2-klein). However, these models present significant…

Real-time 6D object pose estimation is essential for many real-world applications, such as robotic grasping and augmented reality. To achieve an accurate object pose estimation from RGB images in real-time, we propose an effective and…

We propose a human pose estimation framework that solves the task in the regression-based fashion. Unlike previous regression-based methods, which often fall behind those state-of-the-art methods, we formulate the pose estimation task into…

In the era of data-centric AI, the focus of recommender systems has shifted from model-centric innovations to data-centric approaches. The success of modern AI models is built on large-scale datasets, but this also results in significant…

The task of 2D human pose estimation is challenging as the number of keypoints is typically large (~ 17) and this necessitates the use of robust neural network architectures and training pipelines that can capture the relevant features from…

Existing 3D Human Pose Estimation (HPE) methods achieve high accuracy but suffer from computational overhead and slow inference, while knowledge distillation methods fail to address spatial relationships between joints and temporal…

Dataset distillation compresses large datasets into compact synthetic ones to reduce storage and computational costs. Among various approaches, distribution matching (DM)-based methods have attracted attention for their high efficiency.…

Speculative decoding is a powerful technique for reducing the latency of Large Language Models (LLMs), offering a fault-tolerant framework that enables the use of highly compressed draft models. In this work, we introduce Self-Distilled…

We present D-PoSE (Depth as an Intermediate Representation for 3D Human Pose and Shape Estimation), a one-stage method that estimates human pose and SMPL-X shape parameters from a single RGB image. Recent works use larger models with…

Dataset distillation aims to compress information from a large-scale original dataset to a new compact dataset while striving to preserve the utmost degree of the original data informational essence. Previous studies have predominantly…

Recent diffusion distillation methods have achieved remarkable progress, enabling high-quality ${\sim}4$-step sampling for large-scale text-conditional image and video diffusion models. However, further reducing the number of sampling steps…

The computational benefits of iterative non-autoregressive transformers decrease as the number of decoding steps increases. As a remedy, we introduce Distill Multiple Steps (DiMS), a simple yet effective distillation technique to decrease…

Code retrieval aims to provide users with desired code snippets based on users' natural language queries. With the development of deep learning technologies, adopting pre-trained models for this task has become mainstream. Considering the…

In the current state of 6D pose estimation, top-performing techniques depend on complex intermediate correspondences, specialized architectures, and non-end-to-end algorithms. In contrast, our research reframes the problem as a…

Human pose estimation aims to figure out the keypoints of all people in different scenes. Current approaches still face some challenges despite promising results. Existing top-down methods deal with a single person individually, without the…

Recent advances in multimodal models highlight the pivotal role of image tokenization in high-resolution image generation. By compressing images into compact latent representations, tokenizers enable generative models to operate in…

Numerous self-supervised learning paradigms, such as contrastive learning and masked image modeling, have been proposed to acquire powerful and general representations from unlabeled data. However, these models are commonly pretrained…

Distribution system state estimation (DSSE) is an essential tool for operation of distribution networks, the results of which enables the operator to have a thorough observation of the system. Thus, most distribution management systems…