b'Juergen Gall'

research

∙ 08/22/2023

How Much Temporal Long-Term Context is Needed for Action Segmentation?

Modeling long-term context in videos is crucial for many fine-grained ta...

0 Emad Bahrami, et al. ∙

research

∙ 08/18/2023

Smoothness Similarity Regularization for Few-Shot GAN Adaptation

The task of few-shot GAN adaptation aims to adapt a pre-trained GAN mode...

0 Vadim Sushko, et al. ∙

research

∙ 08/12/2023

3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking

Tracking 3D objects accurately and consistently is crucial for autonomou...

0 Shuxiao Ding, et al. ∙

research

∙ 06/26/2023

Action Anticipation with Goal Consistency

In this paper, we address the problem of short-term action anticipation,...

0 Olga Zatsarynna, et al. ∙

research

∙ 06/19/2023

PowerBEV: A Powerful Yet Lightweight Framework for Instance Prediction in Bird's-Eye View

Accurately perceiving instances and predicting their future motion are k...

0 Peizheng Li, et al. ∙

research

∙ 06/09/2023

A Dual-Source Attention Transformer for Multi-Person Pose Tracking

Multi-person pose tracking is an important element for many applications...

0 Andreas Doering, et al. ∙

research

∙ 12/16/2022

Location-aware Adaptive Denormalization: A Deep Learning Approach For Wildfire Danger Forecasting

Climate change is expected to intensify and increase extreme events in t...

0 Mohamad Hakam Shams Eddin, et al. ∙

research

∙ 10/12/2022

Robust Action Segmentation from Timestamp Supervision

Action segmentation is the task of predicting an action label for each f...

0 Yaser Souri, et al. ∙

research

∙ 09/24/2022

Self-supervised Learning for Unintentional Action Prediction

Distinguishing if an action is performed as intended or if an intended a...

0 Olga Zatsarynna, et al. ∙

research

∙ 09/15/2022

One-Shot Synthesis of Images and Segmentation Masks

Joint synthesis of images and segmentation masks with generative adversa...

0 Vadim Sushko, et al. ∙

research

∙ 09/01/2022

Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation

This paper introduces a unified framework for video action segmentation ...

0 Nadine Behrmann, et al. ∙

research

∙ 06/14/2022

Recurrent Transformer Variational Autoencoders for Multi-Action Motion Synthesis

We consider the problem of synthesizing multi-action human motion sequen...

0 Rania Briq, et al. ∙

research

∙ 01/27/2022

Ranking Info Noise Contrastive Estimation: Boosting Contrastive Learning via Ranked Positives

This paper introduces Ranking Info Noise Contrastive Estimation (RINCE),...

7 David T. Hoffmann, et al. ∙

research

∙ 11/30/2021

ATS: Adaptive Token Sampling For Efficient Vision Transformers

While state-of-the-art vision transformer models achieve promising resul...

12 Mohsen Fayyaz, et al. ∙

research

∙ 11/16/2021

Keypoint Message Passing for Video-based Person Re-Identification

Video-based person re-identification (re-ID) is an important technique i...

0 Di Chen, et al. ∙

research

∙ 10/27/2021

Taylor Swift: Taylor Driven Temporal Modeling for Swift Future Frame Prediction

While recurrent neural networks (RNNs) demonstrate outstanding capabilit...

0 Mohammad Saber Pourheydari, et al. ∙

research

∙ 09/23/2021

Long Short View Feature Decomposition via Contrastive Video Representation Learning

Self-supervised video representation methods typically focus on the repr...

0 Nadine Behrmann, et al. ∙

research

∙ 08/09/2021

FIFA: Fast Inference Approximation for Action Segmentation

We introduce FIFA, a fast approximate inference method for action segmen...

7 Yaser Souri, et al. ∙

research

∙ 07/29/2021

Using Visual Anomaly Detection for Task Execution Monitoring

Execution monitoring is essential for robots to detect and respond to fa...

0 Santosh Thoduka, et al. ∙

research

∙ 07/18/2021

Multi-Modal Temporal Convolutional Network for Anticipating Actions in Egocentric Videos

Anticipating human actions is an important task that needs to be address...

0 Olga Zatsarynna, et al. ∙

research

∙ 07/05/2021

Towards Better Adversarial Synthesis of Human Images from Text

This paper proposes an approach that generates multiple 3D human meshes ...

5 Rania Briq, et al. ∙

research

∙ 05/12/2021

Learning to Generate Novel Scene Compositions from Single Images and Videos

Training GANs in low-data regimes remains a challenge, as overfitting of...

0 Vadim Sushko, et al. ∙

research

∙ 03/24/2021

One-Shot GAN: Learning to Generate Samples from Single Images and Videos

Given a large number of training samples, GANs can achieve remarkable pe...

0 Vadim Sushko, et al. ∙

research

∙ 03/11/2021

Temporal Action Segmentation from Timestamp Supervision

Temporal action segmentation approaches have been very successful recent...

0 Zhe Li, et al. ∙

research

∙ 01/24/2021

Iterative Greedy Matching for 3D Human Pose Tracking from Multiple Views

In this work we propose an approach for estimating 3D human poses of mul...

8 Julian Tanke, et al. ∙

research

∙ 01/21/2021

Hierarchical Graph-RNNs for Action Detection of Multiple Activities

In this paper, we propose an approach that spatially localizes the activ...

0 Sovan Biswas, et al. ∙

research

∙ 01/21/2021

Discovering Multi-Label Actor-Action Association in a Weakly Supervised Setting

Since collecting and annotating data for spatio-temporal action detectio...

0 Sovan Biswas, et al. ∙

research

∙ 11/12/2020

PoseTrackReID: Dataset Description

Current datasets for video-based person re-identification (re-ID) do not...

0 Andreas Doering, et al. ∙

research

∙ 11/11/2020

Unsupervised Video Representation Learning by Bidirectional Feature Prediction

This paper introduces a novel method for self-supervised video represent...

0 Nadine Behrmann, et al. ∙

research

∙ 09/02/2020

Long-Term Anticipation of Activities with Cycle Consistency

With the success of deep learning methods in analyzing activities in vid...

2 Yazan Abu Farha, et al. ∙

research

∙ 08/11/2020

Audio- and Gaze-driven Facial Animation of Codec Avatars

Codec Avatars are a recent class of learned, photorealistic face models ...

4 Alexander Richard, et al. ∙

research

∙ 05/19/2020

On Evaluating Weakly Supervised Action Segmentation Methods

Action segmentation is the task of temporally segmenting every frame of ...

0 Yaser Souri, et al. ∙

research

∙ 05/01/2020

Adversarial Synthesis of Human Pose from Text

This work introduces the novel task of human pose synthesis from text. I...

0 Yifei Zhang, et al. ∙

research

∙ 04/27/2020

Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos

Video annotation is expensive and time consuming. Consequently, datasets...

1 Rafi Umer, et al. ∙

research

∙ 03/31/2020

SCT: Set Constrained Temporal Transformer for Set Supervised Action Segmentation

Temporal action segmentation is a topic of increasing interest, however,...

7 Mohsen Fayyaz, et al. ∙

research

∙ 12/30/2019

Discovering Latent Classes for Semi-Supervised Semantic Segmentation

High annotation costs are a major bottleneck for the training of semanti...

15 Johann Sawatzky, et al. ∙

research

∙ 12/13/2019

Bonn Activity Maps: Dataset Description

The key prerequisite for accessing the huge potential of current machine...

28 Julian Tanke, et al. ∙

research

∙ 12/13/2019

Joint Viewpoint and Keypoint Estimation with Real and Synthetic Data

The estimation of viewpoints and keypoints effectively enhance object de...

0 Pau Panareda Busto, et al. ∙

research

∙ 12/12/2019

Human Motion Anticipation with Symbolic Label

Anticipating human motion depends on two factors: the past motion and th...

0 Julian Tanke, et al. ∙

research

∙ 10/10/2019

Cross-modal knowledge distillation for action recognition

In this work, we address the problem how a network for action recognitio...

0 Fida Mohammad Thoker, et al. ∙

research

∙ 08/26/2019

Uncertainty-Aware Anticipation of Activities

Anticipating future activities in video is a task with many practical ap...

0 Yazan Abu Farha, et al. ∙

research

∙ 07/30/2019

Open Set Domain Adaptation for Image and Action Recognition

Since annotating and curating large datasets is very expensive, there is...

1 Pau Panareda Busto, et al. ∙

research

∙ 06/03/2019

A Hybrid RNN-HMM Approach for Weakly Supervised Temporal Action Segmentation

Action recognition has become a rapidly developing research field within...

0 Hilde Kuehne, et al. ∙

research

∙ 06/03/2019

Mining YouTube - A dataset for learning fine-grained action concepts from webly supervised video data

Action recognition is so far mainly focusing on the problem of classific...

0 Hilde Kuehne, et al. ∙

research

∙ 05/16/2019

Harvesting Information from Captions for Weakly Supervised Semantic Segmentation

Since acquiring pixel-wise annotations for training convolutional neural...

0 Johann Sawatzky, et al. ∙

research

∙ 05/15/2019

3D Semantic Scene Completion from a Single Depth Image using Adversarial Training

We address the task of 3D semantic scene completion, i.e. , given a sing...

0 Yueh-Tung Chen, et al. ∙

research

∙ 04/26/2019

Unifying Part Detection and Association for Recurrent Multi-Person Pose Estimation

We propose a joint model of human joint detection and association for 2D...

4 Rania Briq, et al. ∙

research

∙ 04/08/2019

Unsupervised learning of action classes with continuous temporal embedding

The task of temporally detecting and segmenting actions in untrimmed vid...

0 Anna Kukleva, et al. ∙

research

∙ 04/05/2019

Weakly Supervised Action Segmentation Using Mutual Consistency

Action segmentation is the task of predicting the actions in each frame ...

26 Yaser Souri, et al. ∙

research

∙ 04/05/2019

What Object Should I Use? - Task Driven Object Detection

When humans have to solve everyday tasks, they simply pick the objects t...

0 Johann Sawatzky, et al. ∙

Juergen Gall

Featured Co-authors