Tootfinder

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[2/5]:
- Large-scale Pre-training for Grounded Video Caption Generation
Evangelos Kazakos, Cordelia Schmid, Josef Sivic

What Drives Compositional Generalization in Visual Generative Models?
Karim Farid, Rajat Sahay, Yumna Ali Alnaggar, Simon Schrodi, Volker Fischer, Cordelia Schmid, Thomas Brox
https://arxiv.org/abs/2510.03075

What Drives Compositional Generalization in Visual Generative Models?
Compositional generalization, the ability to generate novel combinations of known concepts, is a key ingredient for visual generative models. Yet, not all mechanisms that enable or inhibit it are fully understood. In this work, we conduct a systematic study of how various design choices influence compositional generalization in image and video generation in a positive or negative way. Through controlled experiments, we identify two key factors: (i) whether the training objective operates on a d…

MetricNet: Recovering Metric Scale in Generative Navigation Policies
Abhijeet Nayak, D\'ebora N. P. Oliveira, Samiran Gode, Cordelia Schmid, Wolfram Burgard
https://arxiv.org/abs/2509.13965

MetricNet: Recovering Metric Scale in Generative Navigation Policies
Generative navigation policies have made rapid progress in improving end-to-end learned navigation. Despite their promising results, this paradigm has two structural problems. First, the sampled trajectories exist in an abstract, unscaled space without metric grounding. Second, the control strategy discards the full path, instead moving directly towards a single waypoint. This leads to short-sighted and unsafe actions, moving the robot towards obstacles that a complete and correctly scaled path…

VoCap: Video Object Captioning and Segmentation from Any Prompt
Jasper Uijlings, Xingyi Zhou, Xiuye Gu, Arsha Nagrani, Anurag Arnab, Alireza Fathi, David Ross, Cordelia Schmid
https://arxiv.org/abs/2508.21809

VoCap: Video Object Captioning and Segmentation from Any Prompt
Understanding objects in videos in terms of fine-grained localization masks and detailed semantic properties is a fundamental task in video understanding. In this paper, we propose VoCap, a flexible video model that consumes a video and a prompt of various modalities (text, box or mask), and produces a spatio-temporal masklet with a corresponding object-centric caption. As such our model addresses simultaneously the tasks of promptable video object segmentation, referring expression segmentatio…

Self-lensing binaries as probes of Supernova physics
Grzegorz Wiktorowicz, Matthew Middleton, Aleksandra Olejak, Cordelia Dashwood-Brown, Madeleine-Mai Ward, Adam Ingram
https://arxiv.org/abs/2509.11726

Self-lensing binaries as probes of Supernova physics
Self-lensing (SL) in binary systems has the potential to provide a unique observational window into the Galactic population of compact objects. Using the $\mathtt{startrack}$ and COSMIC population synthesis codes, we investigate how different supernova mechanisms affect the observable population of SL systems, with particular attention to the mass gap (2$\mathrm{-}$5 M$_\odot$) in compact object distributions. We test three supernova remnant formation models with different convective growth tim…

Further evidence for natal kick segregation by spectral type in high-mass X-ray binaries
Pornisara Nuchvanichakul, Poshak Gandhi, Christian Knigge, Yue Zhao, Puji Irawati, Suwicha Wanawichian, Cordelia Dashwood Brown
https://arxiv.org/abs/2509.10221

Further evidence for natal kick segregation by spectral type in high-mass X-ray binaries
High-mass X-ray binaries (HMXBs) are systems in which a neutron star or black hole accretes material from a massive companion. HMXBs are expected to have experienced a supernova in their evolution. The impulsive kick associated with this event should affect the space velocity of the system in a way that depends on the nature and state of the progenitor binary. Here, we test whether the different evolutionary histories of HMXBs have left a detectable imprint on their peculiar velocities ($V_{\rm…