Adapt: Efficient multi-agent trajectory prediction with adaptation
Forecasting future trajectories of agents in complex traffic scenes requires reliable and
efficient predictions for all agents in the scene. However, existing methods for trajectory …
efficient predictions for all agents in the scene. However, existing methods for trajectory …
Rotating features for object discovery
The binding problem in human cognition, concerning how the brain represents and
connects objects within a fixed network of neural connections, remains a subject of intense …
connects objects within a fixed network of neural connections, remains a subject of intense …
Object-centric learning for real-world videos by predicting temporal feature similarities
A Zadaianchuk, M Seitzer… - Advances in Neural …, 2024 - proceedings.neurips.cc
Unsupervised video-based object-centric learning is a promising avenue to learn structured
representations from large, unlabeled video collections, but previous approaches have only …
representations from large, unlabeled video collections, but previous approaches have only …
Slotdiffusion: Object-centric generative modeling with diffusion models
Object-centric learning aims to represent visual data with a set of object entities (aka slots),
providing structured representations that enable systematic generalization. Leveraging …
providing structured representations that enable systematic generalization. Leveraging …
On permutation-invariant neural networks
Conventional machine learning algorithms have traditionally been designed under the
assumption that input data follows a vector-based format, with an emphasis on vector-centric …
assumption that input data follows a vector-based format, with an emphasis on vector-centric …
Compositional scene representation learning via reconstruction: A survey
Visual scenes are composed of visual concepts and have the property of combinatorial
explosion. An important reason for humans to efficiently learn from diverse visual scenes is …
explosion. An important reason for humans to efficiently learn from diverse visual scenes is …
SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers
I Kakogeorgiou, S Gidaris… - Proceedings of the …, 2024 - openaccess.thecvf.com
Unsupervised object-centric learning aims to decompose scenes into interpretable object
entities termed slots. Slot-based auto-encoders stand out as a prominent method for this …
entities termed slots. Slot-based auto-encoders stand out as a prominent method for this …
SlotLifter: Slot-guided Feature Lifting for Learning Object-centric Radiance Fields
The ability to distill object-centric abstractions from intricate visual scenes underpins human-
level generalization. Despite the significant progress in object-centric learning methods …
level generalization. Despite the significant progress in object-centric learning methods …
Exploring the effectiveness of object-centric representations in visual question answering: Comparative insights with foundation models
AMK Mamaghan, S Papa, KH Johansson… - arXiv preprint arXiv …, 2024 - arxiv.org
Object-centric (OC) representations, which represent the state of a visual scene by modeling
it as a composition of objects, have the potential to be used in various downstream tasks to …
it as a composition of objects, have the potential to be used in various downstream tasks to …
Object-centric learning with cyclic walks between parts and whole
Learning object-centric representations from complex natural environments enables both
humans and machines with reasoning abilities from low-level perceptual features. To …
humans and machines with reasoning abilities from low-level perceptual features. To …