Avneesh Sud

Avneesh Sud

Auto-generated profile, based on publicly available information

Avneesh Sud

Google research

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 October 2022
Verified
Book Chapter
Closed access
PDF file
RTReuben Tan
Reuben Tan
BPBryan A. Plummer
Bryan A. Plummer
Kate SaenkoKate Saenko
Kate Saenko
JLJp Lewis
Jp Lewis
ASAvneesh Sud
Avneesh Sud
TLThomas W Leung
Thomas W Leung

14 August 2022 in arXiv
Verified
Preprint
Open access
PDF file
RTReuben Tan
Reuben Tan
BPBryan A. Plummer
Bryan A. Plummer
Kate SaenkoKate Saenko
Kate Saenko
JLJp Lewis
Jp Lewis
ASAvneesh Sud
Avneesh Sud
TLThomas W Leung
Thomas W Leung
Recent self-supervised approaches have used large-scale image-text datasets to learn powerful representations that transfer to many tasks without finetuning. These methods often assume that there is one-to-one correspondence between its images and their (short) captions. However, many tasks require reasoning about multiple images and long text narratives, such as describing news articles with visual summaries. Thus, we explore a novel setting where the goal is to learn a self-supervised visual-language representation that is robust to varying text length and the number of images. In addition, unlike prior work which assumed captions have a literal relation to the image, we assume images only contain loose illustrative correspondence with the text. To explore this problem, we introduce a large-scale multimodal dataset containing over 31M articles, 22M images and 1M videos. We show that state-of-the-art image-text alignment methods are not robust to longer narratives with multiple images. Finally, we introduce an intuitive baseline that outperforms these methods on zero-shot image-set retrieval by 10% on the GoodNews dataset.

26 October 2020 in arXiv
Verified
Preprint
Open access
PDF file
BUBen Usman
Ben Usman
ASAvneesh Sud
Avneesh Sud
NDNick Dufour
Nick Dufour
Kate SaenkoKate Saenko
Kate Saenko
Distribution alignment has many applications in deep learning, including domain adaptation and unsupervised image-to-image translation. Most prior work on unsupervised distribution alignment relies either on minimizing simple non-parametric statistical distances such as maximum mean discrepancy or on adversarial alignment. However, the former fails to capture the structure of complex real-world distributions, while the latter is difficult to train and does not provide any universal convergence guarantees or automatic quantitative validation procedures. In this paper, we propose a new distribution alignment method based on a log-likelihood ratio statistic and normalizing flows. We show that, under certain assumptions, this combination yields a deep neural likelihood-based minimization objective that attains a known lower bound upon convergence. We experimentally verify that minimizing the resulting objective results in domain alignment that preserves the local structure of input domains.

26 November 2021 in arXiv
Verified
Preprint
Open access
PDF file
BUBen Usman
Ben Usman
ATAndrea Tagliasacchi
Andrea Tagliasacchi
Kate SaenkoKate Saenko
Kate Saenko
ASAvneesh Sud
Avneesh Sud
In the era of deep learning, human pose estimation from multiple cameras with unknown calibration has received little attention to date. We show how to train a neural model to perform this task with high precision and minimal latency overhead. The proposed model takes into account joint location uncertainty due to occlusion from multiple views, and requires only 2D keypoint data for training. Our method outperforms both classical bundle adjustment and weakly-supervised monocular 3D baselines on the well-established Human3.6M dataset, as well as the more challenging in-the-wild Ski-Pose PTZ dataset.