38 citations · 43 across the 5 of their papers we have counts for
6 papers
BulletTime: Decoupled Control of Time and Camera Pose for Video Generation
Yiming Wang, Qihang Zhang, Shengqu Cai +7
Emerging video diffusion models achieve high visual fidelity but fundamentally couple scene dynamics with camera motion, limiting their ability to provide precise spatial and tempo…
Multi-View 3D Point Tracking
Frano Rajič, Haofei Xu, Marko Mihajlovic +7
We introduce the first data-driven multi-view 3D point tracker, designed to track arbitrary points in dynamic scenes using multiple camera views. Unlike existing monocular trackers…
Sim-to-Real Causal Transfer: A Metric Learning Approach to Causally-Aware Interaction Representations
Ahmad Rahimi, Po-Chien Luan, Yuejiang Liu +2
Modeling spatial-temporal interactions among neighboring agents is at the heart of multi-agent problems such as motion forecasting and crowd navigation. Despite notable progress, i…
Segment Anything Meets Point Tracking
Frano Rajič, Lei Ke, Yu-Wing Tai +3
The Segment Anything Model (SAM) has established itself as a powerful zero-shot image segmentation model, enabled by efficient point-centric annotation and prompt-based models. Whi…
Using Focal Loss to Fight Shallow Heuristics: An Empirical Analysis of Modulated Cross-Entropy in Natural Language Inference
Frano Rajič, Ivan Stresec, Axel Marmet +1
There is no such thing as a perfect dataset. In some datasets, deep neural networks discover underlying heuristics that allow them to take shortcuts in the learning process, result…
Language Model Decoding as Likelihood-Utility Alignment
Martin Josifoski, Maxime Peyrard, Frano Rajic +8
A critical component of a successful language generation pipeline is the decoding algorithm. However, the general principles that should guide the choice of a decoding algorithm re…