HOLA introduces multi-view multi-text alignment and a decoupled contrastive loss for state-of-the-art open-vocabulary 3D recognition on long-tail benchmarks.
Self-supervised representation learning with relative predictive coding
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
AmelPredSto, a stochastic self-predictive representation model, outperforms other state representation learning approaches when combined with actor-critic RL for object-goal navigation in UAVs.
citing papers explorer
-
HOLA: Holistic Multi-Modal Alignment for Open-Set 3D Recognition
HOLA introduces multi-view multi-text alignment and a decoupled contrastive loss for state-of-the-art open-vocabulary 3D recognition on long-tail benchmarks.
-
Self-Predictive Representation for Autonomous UAV Object-Goal Navigation
AmelPredSto, a stochastic self-predictive representation model, outperforms other state representation learning approaches when combined with actor-critic RL for object-goal navigation in UAVs.