Swathikiran Sudhakaran

Swathikiran Sudhakaran

Auto-generated profile, based on publicly available information

Swathikiran Sudhakaran

Fondazione Bruno Kessler

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
1 August 2017
Verified
Conference Paper
Closed access
SSSwathikiran Sudhakaran
Swathikiran Sudhakaran
OLOswald Lanz
Oswald Lanz
Developing a technique for the automatic analysis of surveillance videos in order to identify the presence of violence is of broad interest. In this work, we propose a deep neural network for the purpose of recognizing violent videos. A convolutional neural network is used to extract frame level features from a video. The frame level features are then aggregated using a variant of the long short term memory that uses convolutional gates. The convolutional neural network along with the convolutional long short term memory is capable of capturing localized spatio-temporal features which enables the analysis of local motion taking place in the video. We also propose to use adjacent frame differences as the input to the model thereby forcing it to encode the changes occurring in the video. The performance of the proposed feature extraction pipeline is evaluated on three standard benchmark datasets in terms of recognition accuracy. Comparison of the results obtained with the state of the art techniques revealed the promising capability of the proposed method in recognizing violent videos.

19 April 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
SSSwathikiran Sudhakaran
Swathikiran Sudhakaran
Sergio EscaleraSergio Escalera
Sergio Escalera
OLOswald Lanz
Oswald Lanz
Convolutional Neural Networks are the de facto models for image recognition. However 3D CNNs, the straight forward extension of 2D CNNs for video recognition, have not achieved the same success on standard action recognition benchmarks. One of the main reasons for this reduced performance of 3D CNNs is the increased computational complexity requiring large scale annotated datasets to train them in scale. 3D kernel factorization approaches have been proposed to reduce the complexity of 3D CNNs. Existing kernel factorization approaches follow hand-designed and hard-wired techniques. In this paper we propose Gate-Shift-Fuse (GSF), a novel spatio-temporal feature extraction module which controls interactions in spatio-temporal decomposition and learns to adaptively route features through time and combine them in a data dependent manner. GSF leverages grouped spatial gating to decompose input tensor and channel weighting to fuse the decomposed tensors. GSF can be inserted into existing 2D CNNs to convert them into an efficient and high performing spatio-temporal feature extractor, with negligible parameter and compute overhead. We perform an extensive analysis of GSF using two popular 2D CNN families and achieve state-of-the-art or competitive performance on five standard action recognition benchmarks.

1 October 2017
Verified
Conference Paper
Closed access
SSSwathikiran Sudhakaran
Swathikiran Sudhakaran
OLOswald Lanz
Oswald Lanz
In this paper, we present a novel deep learning based approach for addressing the problem of interaction recognition from a first person perspective. The proposed approach uses a pair of convolutional neural networks, whose parameters are shared, for extracting frame level features from successive frames of the video. The frame level features are then aggregated using a convolutional long shortterm memory. The hidden state of the convolutional long short-term memory, after all the input video frames are processed, is used for classification in to the respective categories. The two branches of the convolutional neural network perform feature encoding on a short time interval whereas the convolutional long short term memory encodes the changes on a longer temporal duration. In our network the spatio-temporal structure of the input is preserved till the very final processing stage. Experimental results show that our method outperforms the state of the art on most recent first person interactions datasets that involve complex ego-motion. In particular, on UTKinect-FirstPerson it competes with methods that use depth image and skeletal joints information along with RGB images, while it surpasses all previous methods that use only RGB images by more than 20% in recognition accuracy.

11 February 2021 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
SSSwathikiran Sudhakaran
Swathikiran Sudhakaran
Sergio EscaleraSergio Escalera
Sergio Escalera
OLOswald Lanz
Oswald Lanz
We present EgoACO, a deep neural architecture for video action recognition that learns to pool action-context-object descriptors from frame level features by leveraging the verb-noun structure of action labels in egocentric video datasets. The core component is class activation pooling (CAP), a differentiable pooling layer that combines ideas from bilinear pooling for fine-grained recognition and from feature learning for discriminative localization. CAP uses self-attention with a dictionary of learnable weights to pool from the most relevant feature regions. Through CAP, EgoACO learns to decode object and scene context descriptors from video frame features. For temporal modeling we design a recurrent version of class activation pooling termed Long Short-Term Attention (LSTA). LSTA extends convolutional gated LSTM with built-in spatial attention and a re-designed output gate. Action, object and context descriptors are fused by a multi-head prediction that accounts for the inter-dependencies between noun-verb-action structured labels in egocentric video datasets. EgoACO features built-in visual explanations, helping learning and interpretation of discriminative information in video. Results on the two largest egocentric action recognition datasets currently available, EPIC-KITCHENS and EGTEA Gaze+, show that by decoding action-context-object descriptors, the model achieves state-of-the-art recognition performance.

1 September 2014
Verified
Conference Paper
Closed access
NKNeethu S. Kumar
Neethu S. Kumar
DKDinesh S. Kumar
Dinesh S. Kumar
SSS. Swathikiran
S. Swathikiran
AJAlex P James
Alex P James
In this work, we propose a character segmentation system from ancient palm leaf manuscripts written in ancient Arya Ezhuthu(which was popularized as script to write Malayalam from 17th century). The automatic recognition of handwritten text from digital images of palm leaves dating back to 10th century BC. This can enable context based searching in large volumes of digital document. The subject about document image understanding is to extract and classify individual data meaningfully from palm leaf manuscript. We propose an automatic approach to detecting and identifying the characters. The proposed approach can improve the readability of the document. Text line segmentation is then applied and the characters are extracted.

2 September 2019
Verified
Book Chapter
Closed access
PDF file
SSSudipan Saha
Sudipan Saha
SSSwathikiran Sudhakaran
Swathikiran Sudhakaran
BBBiplab Banerjee
Biplab Banerjee
SPSumedh Pendurkar
Sumedh Pendurkar