Related papers: Multi-Grained Feature Pruning for Video-Based Huma…

Online video understanding is essential for applications like public surveillance and AI glasses. However, applying Multimodal Large Language Models (MLLMs) to this domain is challenging due to the large number of video frames, resulting in…

In this paper we consider the problem of human pose estimation from a single still image. We propose a novel approach where each location in the image votes for the position of each keypoint using a convolutional neural net. The voting…

Estimating 3D poses from a monocular video is still a challenging task, despite the significant progress that has been made in recent years. Generally, the performance of existing methods drops when the target person is too small/large, or…

Large Vision-Language Models (LVLMs) have shown impressive performance across multi-modal tasks by encoding images into thousands of tokens. However, the large number of image tokens results in significant computational overhead, and the…

We propose a method to estimate 3D human poses from substantially blurred images. The key idea is to tackle the inverse problem of image deblurring by modeling the forward problem with a 3D human model, a texture map, and a sequence of…

We present a box-free bottom-up approach for the tasks of pose estimation and instance segmentation of people in multi-person images using an efficient single-shot model. The proposed PersonLab model tackles both semantic-level reasoning…

The typical bottom-up human pose estimation framework includes two stages, keypoint detection and grouping. Most existing works focus on developing grouping algorithms, e.g., associative embedding, and pixel-wise keypoint regression that we…

Real-time robotic grasping, supporting a subsequent precise object-in-hand operation task, is a priority target towards highly advanced autonomous systems. However, such an algorithm which can perform sufficiently-accurate grasping with…

Holistic methods based on dense trajectories are currently the de facto standard for recognition of human activities in video. Whether holistic representations will sustain or will be superseded by higher level video encoding in terms of…

Visual localization remains challenging in dynamic environments where fluctuating lighting, adverse weather, and moving objects disrupt appearance cues. Despite advances in feature representation, current absolute pose regression methods…

This paper addresses the challenge of 3D full-body human pose estimation from a monocular image sequence. Here, two cases are considered: (i) the image locations of the human joints are provided and (ii) the image locations of joints are…

This paper considers the task of articulated human pose estimation of multiple people in real world images. We propose an approach that jointly solves the tasks of detection and pose estimation: it infers the number of persons in a scene,…

We present a bundle-adjustment-based algorithm for recovering accurate 3D human pose and meshes from monocular videos. Unlike previous algorithms which operate on single frames, we show that reconstructing a person over an entire sequence…

Pose estimation is a vital step in many robotics and perception tasks such as robotic manipulation, autonomous vehicle navigation, etc. Current state-of-the-art pose estimation methods rely on deep neural networks with complicated…

Reasoning human object interactions is a core problem in human-centric scene understanding and detecting such relations poses a unique challenge to vision systems due to large variations in human-object configurations, multiple co-occurring…

The attention mechanism provides a sequential prediction framework for learning spatial models with enhanced implicit temporal consistency. In this work, we show a systematic design (from 2D to 3D) for how conventional networks and other…

Reliable three-dimensional human pose estimation (3D HPE) remains challenging due to the differences in viewpoints, environments, and camera conventions among datasets. As a result, methods that achieve near-optimal in-dataset accuracy…

We propose a personalized ConvNet pose estimator that automatically adapts itself to the uniqueness of a person's appearance to improve pose estimation in long videos. We make the following contributions: (i) we show that given a few…

Existing pruning techniques preserve deep neural networks' overall ability to make correct predictions but may also amplify hidden biases during the compression process. We propose a novel pruning method, Fairness-aware GRAdient Pruning…

We propose a general and versatile framework that significantly speeds-up graphical model optimization while maintaining an excellent solution accuracy. The proposed approach relies on a multi-scale pruning scheme that is able to…