DSpace Repository

Browsing Proceedings papers by Author "DABRAL R."

Browsing Proceedings papers by Author "DABRAL R."

Sort by: Order: Results:

  • Cross Lingual Video and Text Retrieval: A New Benchmark Dataset and Algorithm 
    AKULA J.; ABHISHEK; DABRAL R.; JYOTHI P.; RAMAKRISHNAN G. (Association for Computing Machinery, Inc, 2021)
    Video retrieval using natural language queries requires learning semantically meaningful joint embeddings between the text and the audio-visual input. Often, such joint embeddings are learnt using pairwise (or triplet) ...
  • Cross-modal learning for audio-visual video parsing 
    LAMBA J.; THAKUR A.; AKULA J.; DABRAL R.; JYOTHI P.; RAMAKRISHNAN G. (International Speech Communication Association, 2021)
    In this paper, we present a novel approach to the audio-visual video parsing (avvp) task that demarcates events from a video separately for audio and visual modalities. The proposed parsing approach simultaneously detects ...
  • Exploration of spatial and temporal modeling alternatives for HOI 
    DABRAL R.; SARKAR S.; REDDY S.P.; RAMAKRISHNAN G. (Institute of Electrical and Electronics Engineers Inc., 2021)
    Human-object interaction detection from a video clip can be considered as a special case of video-based visual-relationship detection wherein the subject must be a human. Specifically, it involves detecting the humans and ...
  • Gravity-Aware Monocular 3D Human-Object Reconstruction 
    DABRAL R.; SHIMADA S.; JAIN A.; THEOBALT C.; GOLYANIK V. (Institute of Electrical and Electronics Engineers Inc., 2021)
    This paper proposes gravicap, i.e., A new approach for joint markerless 3d human motion capture and object trajectory estimation from monocular rgb videos. We focus on scenes with objects partially observed during a free ...
  • Learning unsupervised cross-domain image-to-image translation using a shared discriminator 
    KUMAR R.; DABRAL R.; SIVAKUMAR G. (SciTePress, 2021)
    Unsupervised image-to-image translation is used to transform images from a source domain to generate images in a target domain without using source-target image pairs. Promising results have been obtained for this problem ...

Search DSpace


Advanced Search

Browse

My Account