Litcius/Paper detail

D$$^3$$Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding

Dave Zhenyu Chen, Qirui Wu, Matthias Nießner, Anne Lynn S. Chang

2022Lecture notes in computer science35 citationsDOI

Topics & Concepts

Closed captioningComputer scienceOverfittingDiscriminative modelArtificial intelligenceMargin (machine learning)Natural language processingVisualizationSpeech recognitionArtificial neural networkPattern recognition (psychology)Image (mathematics)Machine learningMultimodal Machine Learning ApplicationsHuman Pose and Action RecognitionAdvanced Image and Video Retrieval Techniques
D$^3$Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding | Litcius