paper-with-me

홈 › Papers

Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds

2022-04-22 · Heng Wang, Chaoyi Zhang, Jianhui Yu, Weidong Cai

Dense captioning in 3D point clouds is an emerging vision-and-language task involving object-level 3D scene understanding. Apart from coarse semantic class prediction and bounding box regression as in traditional 3D object detection, 3D dense captioning aims at producing a further and finer instance-level label of natural language description on visual appearance and spatial relations for each scene object of interest. To detect and describe objects in a scene, following the spirit of neural machine translation, we propose a transformer-based encoder-decoder architecture, namely SpaCap3D, to transform objects into descriptions, where we especially investigate the relative spatiality of objects in 3D scenes and design a spatiality-guided encoder via a token-to-token spatial relation learning objective and an object-centric decoder for precise and spatiality-enhanced object caption generation. Evaluated on two benchmark datasets, ScanRefer and ReferIt3D, our proposed SpaCap3D outperforms the baseline method Scan2Cap by 4.94% and 9.61% in CIDEr@0.5IoU, respectively. Our project page with source code and supplementary files is available at https://SpaCap3D.github.io/ .

📄 PDF Abstract BibTeX arXiv:2204.10688

Code (1)

heng-hw/spacap3d 공식 구현 pytorch

Tasks

3D dense captioning3D Object DetectionCaption GenerationDecoderDense CaptioningMachine TranslationObjectobject-detectionObject DetectionScene Understanding

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Adam 설명 없음

Similar Papers 제목 키워드 기반

X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning

2022-03-02 · CVPR 2022 1 · Zhihao Yuan, Xu Yan, Yinghong Liao, Yao Guo 외

3D dense captioning aims to describe individual objects by natural language in 3D scenes, where 3D scenes are usually represented as RGB-D scans or point clouds. However, only exploiting single modal information, e.g., p…

3D dense captioningDense CaptioningKnowledge DistillationTransfer Learning

End-to-End Dense Video Captioning with Masked Transformer

2018-04-03 · CVPR 2018 4 · Luowei Zhou, Yingbo Zhou, Jason J. Corso, Richard Socher 외

Dense video captioning aims to generate text descriptions for all events in an untrimmed video. This involves both detecting and describing events. Therefore, all previous methods on dense video captioning tackle this pr…

DecoderDense Video CaptioningVideo Captioning

UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Grounding

2022-12-01 · ICCV 2023 1 · Dave Zhenyu Chen, Ronghang Hu, Xinlei Chen, Matthias Nießner 외

Performing 3D dense captioning and visual grounding requires a common and shared understanding of the underlying multimodal relationships. However, despite some previous attempts on connecting these two related tasks wit…

3D dense captioning3D visual groundingDense CaptioningVisual Grounding

A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer

2020-05-17 · Vladimir Iashin, Esa Rahtu

Dense video captioning aims to localize and describe important events in untrimmed videos. Existing methods mainly tackle this task by exploiting only visual features, while completely neglecting the audio track. Only a …

Dense Video CaptioningTemporal Action Proposal GenerationVideo Captioning

See It All: Contextualized Late Aggregation for 3D Dense Captioning

2024-08-14 · Minjung Kim, Hyung Suk Lim, Seung Hwan Kim, Soonyoung Lee 외

3D dense captioning is a task to localize objects in a 3D scene and generate descriptive sentences for each object. Recent approaches in 3D dense captioning have adopted transformer encoder-decoder frameworks from object…

3D dense captioningAllAttributeCaption Generation+6