activity
20152026
most citedMOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking

650 citations · 762 across the 17 of their papers we have counts for

collaborators
Showing 2019Show all

9 papers · 1 filter

cs.RO2019

Driving Style Encoder: Situational Reward Adaptation for General-Purpose Planning in Automated Driving

Sascha Rosbach, Vinit James, Simon Großjohann +3

General-purpose planning algorithms for automated driving combine mission, behavior, and local motion planning. Such planning algorithms map features of the environment and driving…

cs.CV2019

Markov Decision Process for Video Generation

Vladyslav Yushchenko, Nikita Araslanov, Stefan Roth

We identify two pathological cases of temporal inconsistencies in video generation: video freezing and video looping. To better quantify the temporal diversity, we propose a class…

cs.CV2019

Deep Video Deblurring: The Devil is in the Details

Jochen Gast, Stefan Roth

Video deblurring for hand-held cameras is a challenging task, since the underlying blur is caused by both camera shake and object motion. State-of-the-art deep networks exploit tem…

cs.CV2019

Joint Wasserstein Autoencoders for Aligning Multimodal Embeddings

Shweta Mahajan, Teresa Botschen, Iryna Gurevych +1

One of the key challenges in learning joint embeddings of multiple modalities, e.g. of images and text, is to ensure coherent cross-modal semantics that generalize across datasets.…

cs.CV2019

Learning Task-Specific Generalized Convolutions in the Permutohedral Lattice

Anne S. Wannenwetsch, Martin Kiefel, Peter V. Gehler +1

Dense prediction tasks typically employ encoder-decoder architectures, but the prevalent convolutions in the decoder are not image-adaptive and can lead to boundary artifacts. Diff…

cs.CV201968 cited

CVPR19 Tracking and Detection Challenge: How crowded can it get?

Patrick Dendorfer, Hamid Rezatofighi, Anton Milan +6

Standardized benchmarks are crucial for the majority of computer vision applications. Although leaderboards and ranking tables should not be over-claimed, benchmarks often provide…