paper-with-me

Papers

Towards Generalizing Temporal Action Segmentation to Unseen Views

2025-04-03 · Emad Bahrami, Olga Zatsarynna, Gianpiero Francesca, Juergen Gall

While there has been substantial progress in temporal action segmentation, the challenge to generalize to unseen views remains unaddressed. Hence, we define a protocol for unseen view action segmentation where camera views for evaluating the model are unavailable during training. This includes changing from top-frontal views to a side view or even more challenging from exocentric to egocentric views. Furthermore, we present an approach for temporal action segmentation that tackles this challenge. Our approach leverages a shared representation at both the sequence and segment levels to reduce the impact of view differences during training. We achieve this by introducing a sequence loss and an action loss, which together facilitate consistent video and action representations across different views. The evaluation on the Assembly101, IkeaASM, and EgoExoLearn datasets demonstrate significant improvements, with a 12.8% increase in F1@50 for unseen exocentric views and a substantial 54% improvement for unseen egocentric views.

📄 PDF Abstract BibTeX arXiv:2504.02512

Code (0)

등록된 구현이 없습니다.

Tasks

Action SegmentationSegmentationTemporal Action Segmentation

Similar Papers 제목 키워드 기반

Cascaded and Generalizable Neural Radiance Fields for Fast View Synthesis

2022-08-09 · Phong Nguyen-Ha, Lam Huynh, Esa Rahtu, Jiri Matas 외

We present CG-NeRF, a cascade and generalizable neural radiance fields method for view synthesis. Recent generalizing view synthesis methods can render high-quality novel views using a set of nearby input views. However,…

GPUNeRFNeural RenderingNovel View Synthesis

KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypoints

2022-05-10 · Marko Mihajlovic, Aayush Bansal, Michael Zollhoefer, Siyu Tang 외

Image-based volumetric humans using pixel-aligned features promise generalization to unseen poses and identities. Prior work leverages global spatial encodings and multi-view geometric consistency to reduce spatial ambig…

3D Face Reconstruction3D Human ReconstructionGeneralizable Novel View SynthesisNovel View Synthesis

LatentHOI: On the Generalizable Hand Object Motion Generation with Latent Hand Diffusion.

2025-01-01 · CVPR 2025 1 · Muchen Li, Sammy Christen, Chengde Wan, Yujun Cai 외

Current research on generating 3D hand-object interaction motion primarily focuses on in-domain objects. Generalization to unseen objects is essential for practical applications, yet it remains both challenging and l…

Motion GenerationObject

Generalizing Word Embeddings using Bag of Subwords

2018-09-12 · EMNLP 2018 10 · Jinman Zhao, Sidharth Mudgal, YIngyu Liang

We approach the problem of generalizing pre-trained word embeddings beyond fixed-size vocabularies without using additional contextual information. We propose a subword-level word vector generation model that views words…

TAGWord EmbeddingsWord Similarity

OG-VLA: 3D-Aware Vision Language Action Model via Orthographic Image Generation

2025-06-01 · Ishika Singh, Ankit Goyal, Stan Birchfield, Dieter Fox 외

We introduce OG-VLA, a novel architecture and learning framework that combines the generalization strengths of Vision Language Action models (VLAs) with the robustness of 3D-aware policies. We address the challenge of ma…

Image GenerationLarge Language ModelRobot ManipulationVision-Language-Action