31 citations · 60 across the 16 of their papers we have counts for
17 papers
ClimateVID -- Social Media Videos Analysis and Challenges Involved
Shiqi Xu, Moritz Burmester, Katharina Prasse +3
The pervasive growth of digital content, specifically short videos on social media platforms, has significantly altered how topics are discussed and understood in public discourse.…
From Codebooks to VLMs: Evaluating Automated Visual Discourse Analysis for Climate Change on Social Media
Katharina Prasse, Steffen Jung, Isaac Bravo +4
Social media platforms have become primary arenas for climate communication, generating millions of images and posts that - if systematically analysed - can reveal which communicat…
MaxSup: Overcoming Representation Collapse in Label Smoothing
Yuxuan Zhou, Heng Li, Zhi-Qi Cheng +4
Label Smoothing (LS) is widely adopted to reduce overconfidence in neural network predictions and improve generalization. Despite these benefits, recent studies reveal two critical…
Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation
Yuxuan Zhou, Margret Keuper, Mario Fritz
Sampling-based decoding strategies have been widely adopted for Large Language Models (LLMs) in numerous applications, targeting a balance between diversity and quality via tempera…
MultiMax: Sparse and Multi-Modal Attention Learning
Yuxuan Zhou, Mario Fritz, Margret Keuper
SoftMax is a ubiquitous ingredient of modern machine learning algorithms. It maps an input vector onto a probability simplex and reweights the input by concentrating the probabilit…
VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis
Yumeng Li, William Beluch, Margret Keuper +2
Despite tremendous progress in the field of text-to-video (T2V) synthesis, open-sourced T2V diffusion models struggle to generate longer videos with dynamically varying and evolvin…
Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive
Yumeng Li, Margret Keuper, Dan Zhang +1
Despite the recent advances in large-scale diffusion models, little progress has been made on the layout-to-image (L2I) synthesis task. Current L2I models either suffer from poor e…
Local Spherical Harmonics Improve Skeleton-Based Hand Action Recognition
Katharina Prasse, Steffen Jung, Yuxuan Zhou +1
Hand action recognition is essential. Communication, human-robot interactions, and gesture control are dependent on it. Skeleton-based action recognition traditionally includes han…
Intra- & Extra-Source Exemplar-Based Style Synthesis for Improved Domain Generalization
Yumeng Li, Dan Zhang, Margret Keuper +1
The generalization with respect to domain shifts, as they frequently appear in applications such as autonomous driving, is one of the remaining big challenges for deep learning mod…
Divide & Bind Your Attention for Improved Generative Semantic Nursing
Yumeng Li, Margret Keuper, Dan Zhang +1
Emerging large-scale text-to-image generative models, e.g., Stable Diffusion (SD), have exhibited overwhelming results with high fidelity. Despite the magnificent progress, current…
Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness
Yuxuan Zhou, Zhi-Qi Cheng, Jun-Yan He +3
Graph Convolutional Networks (GCNs) have long defined the state-of-the-art in skeleton-based action recognition, leveraging their ability to unravel the complex dynamics of human j…
Hypergraph Transformer for Skeleton-based Action Recognition
Yuxuan Zhou, Zhi-Qi Cheng, Chao Li +4
Skeleton-based action recognition aims to recognize human actions given human joint coordinates with skeletal interconnections. By defining a graph with joints as vertices and thei…
Intra-Source Style Augmentation for Improved Domain Generalization
Yumeng Li, Dan Zhang, Margret Keuper +1
The generalization with respect to domain shifts, as they frequently appear in applications such as autonomous driving, is one of the remaining big challenges for deep learning mod…
SP-ViT: Learning 2D Spatial Priors for Vision Transformers
Yuxuan Zhou, Wangmeng Xiang, Chao Li +5
Recently, transformers have shown great potential in image classification and established state-of-the-art results on the ImageNet benchmark. However, compared to CNNs, transformer…
Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis
Yang He, Ning Yu, Margret Keuper +1
The rapid advances in deep generative models over the past years have led to highly {realistic media, known as deepfakes,} that are commonly indistinguishable from real to human ey…
Learning Dilation Factors for Semantic Segmentation of Street Scenes
Yang He, Margret Keuper, Bernt Schiele +1
Contextual information is crucial for semantic segmentation. However, finding the optimal trade-off between keeping desired fine details and at the same time providing sufficiently…
STD2P: RGBD Semantic Segmentation Using Spatio-Temporal Data-Driven Pooling
Yang He, Wei-Chen Chiu, Margret Keuper +1
We propose a novel superpixel-based multi-view convolutional neural network for semantic image segmentation. The proposed network produces a high quality segmentation of a single i…