DAS , Srijan

Manipulated images and videos, i.e., deepfakes have become increasingly realistic due to the tremendous progress of deep learning methods. However, such manipulation has triggered social concerns, necessitating the introduction of robust and reliable methods for deepfake detection. In this work, we explore a set of attention mechanisms and...

This thesis targets recognition of human actions in videos. Action recognition is a complicated task in the field of computer vision due to its high complex challenges. With the emergence of deep learning and large scale datasets from internet sources, substantial improvements have been made in video understanding. For instance,...

This thesis targets recognition of human actions in videos. Action recognition is a complicated task in the field of computer vision due to its high complex challenges. With the emergence of deep learning and large scale datasets from internet sources, substantial improvements have been made in video understanding. For instance,...

This work explores various ways of exploring multi-task learning (MTL) techniques aimed at classifying videos as original or manipulated in cross-manipulation scenario to attend generalizability in deep fake scenario. The dataset used in our evaluation is FaceForensics++, which features 1000 original videos manipulated by four different...

Video anomaly detection under weak supervision is complicated due to the difficulties in identifying the anomaly and normal instances during training, hence, resulting in non-optimal margin of separation. In this paper, we propose a framework consisting of Dissimilarity Attention Module (DAM) to discriminate the anomaly instances from normal...

Action detection is an essential and challenging task, especially for densely labelled datasets of untrimmed videos. There are many real-world challenges in those datasets, such as composite action, co-occurring action, and high temporal variation of instance duration. For handling these challenges, we propose to explore both the class and...

In this paper, we introduce a new approach for Activities of Daily Living (ADL) recognition. In order to discriminate between activities with similar appearance and motion, we focus on their temporal structure. Actions with subtle and similar motion are hard to disambiguate since long-range temporal information is hard to encode. So, we propose...

In video understanding, most cross-modal knowledge distillation (KD) methods are tailored for classification tasks, focusing on the discriminative representation of the trimmed videos. However, action detection requires not only categorizing actions, but also localizing them in untrimmed videos. Therefore, transferring knowledge pertaining to...

In this paper, we present a new attention model for the recognition of human action from RGB-D videos. We propose an attention mechanism based on 3D articulated pose. The objective is to focus on the most relevant body parts involved in the action. For action classification, we propose a classification network compounded of spatio-temporal...

This paper address the recognition of short-term daily living actions from RGB-D videos. The existing approaches ignore spatio-temporal contextual relationships in the action videos. So, we propose to explore the spatial layout to better model the appearance. In order to encode temporal information, we divide the action sequence into temporal...

In this paper, we propose to improve the traditional use of RNNs by employing a many to many model for video classification. We analyze the importance of modeling spatial layout and temporal encoding for daily living action recognition. Many RGB methods focus only on short term temporal information obtained from optical flow. Skeleton based...

In this paper, we study how different skeleton extraction methods affect the performance of action recognition. As shown in previous work skeleton information can be exploited for action recognition. Nevertheless, skeleton detection problem is already hard and very often it is difficult to obtain reliable skeleton information from videos. In...

Many attempts have been made towards combining RGB and 3D poses for the recognition of Activities of Daily Living (ADL). ADL may look very similar and often necessitate to model fine-grained details to distinguish them. Because the recent 3D ConvNets are too rigid to capture the subtle visual patterns across an action, this research direction...

The challenge of long-term video understanding remains constrained by the efficient extraction of object semantics and the modelling of their relationships for downstream tasks. Although OpenAI's CLIP visual features exhibit discriminative properties for various vision tasks, particularly in object encoding, they are suboptimal for long-term...

Action detection is a significant and challenging task, especially in densely-labelled datasets of untrimmed videos. Such data consist of complex temporal relations including composite or co-occurring actions. To detect actions in these complex settings, it is critical to capture both shortterm and long-term temporal information efficiently. To...

Anomaly activities such as robbery, explosion, accidents, etc. need immediate actions for preventing loss of human life and property in real world surveillance systems. Although the recent automation in surveillance systems are capable of detecting the anomalies, but they still need human efforts for categorizing the anomalies and taking...

In this paper, we focus on the spatio-temporal aspect of recognizing Activities of Daily Living (ADL). ADL have two specific properties (i) subtle spatio-temporal patterns and (ii) similar visual patterns varying with time. Therefore, ADL may look very similar and often necessitate to look at their fine-grained details to distinguish them....

Activity Recognition from RGB-D videos is still an open problem due to the presence of large varieties of actions. In this work, we propose a new architecture by mixing a high level handcrafted strategy and machine learning techniques. We propose a novel two level fusion strategy to combine features from different cues to address the problem of...

Handling long and complex temporal information is an important challenge for action detection tasks. This challenge is further aggravated by densely distributed actions in untrimmed videos. Previous action detection methods fail in selecting the key temporal information in long videos. To this end, we introduce the Dilated Attention Layer...

The performance of deep neural networks is strongly influenced by the quantity and quality of annotated data. Most of the large activity recognition datasets consist of data sourced from the web, which does not reflect challenges that exist in activities of daily living. In this paper, we introduce a large real-world video dataset for...

Designing activity detection systems that can be successfully deployed in daily-living environments requires datasets that pose the challenges typical of real-world scenarios. In this paper, we introduce a new untrimmed daily-living dataset that features several real-world challenges: Toyota Smarthome Untrimmed (TSU). TSU contains a wide...