Abstract

We present GAZED– eye GAZ-guided EDiting for videos captured by a solitary, static, wide-angle and high-resolution camera. Eye-gaze has been effectively employed in computational applications as a cue to capture interesting scene content; we employ gaze as a proxy to select shots for inclusion in the edited video. Given the original video, scene content and user eye-gaze tracks are combined to generate an edited video comprising of cinematically valid actor shots and shot transitions to generate an aesthetic and vivid representation of the original narrative. We model cinematic video editing as an energy minimization problem over shot selection, whose constraints capture cinematographic editing conventions. Gazed scene locations primarily determine the shots constituting the edited video. Effectiveness of GAZED against multiple competing methods is demonstrated via a psychophysical study involving 12 users and twelve performance videos. Professional video recordings of stage performances are typically created by employing skilled camera operators, who record the performance from multiple viewpoints. These multi-camera feeds, termed rushes, are then edited together to portray an eloquent story intended to maximize viewer engagement. Generating professional edits of stage performances is both difficult and challenging. Firstly, maneuvering cameras during a live performance is difficult even for experts as there is no option of retake upon error, and camera viewpoints are limited as the use of large supporting equipment (trolley, crane .) is infeasible. Secondly, manual video editing is an extremely slow and tedious process and leverages the experience of skilled editors. Overall, the need for (i) a professional camera crew, (ii) multiple cameras and supporting equipment, and (iii) expert editors escalates the process complexity and costs. Consequently, most production houses employ a large field-of-view static camera, placed far enough to capture the entire stage. This approach is widespread as it is simple to implement, and also captures the entire scene. Such static visualizations are apt for archival purposes; however, they are often unsuccessful at captivating attention when presented to the target audience. While conveying the overall context, the distant camera feed fails to bring out vivid scene details like close-up faces, character emotions and actions, and ensuing interactions which are critical for cinematic storytelling. GAZED denotes an end-to-end pipeline to generate an aesthetically edited video from a single static, wide-angle stage recording. This is inspired by prior work [GRG14], which describes how a plural camera crew can be replaced by a single highresolution static camera, and multiple virtual camera shots or rushes generated by simulating several virtual pan/tilt/zoom cameras to focus on actors and actions within the original recording. In this work, we demonstrate that the multiple rushes can be automatically edited by leveraging user eye gaze information, by modeling (virtual) shot selection as a discrete optimization problem. Eye-gaze represents an inherent guiding factor for video editing, as eyes are sensitive to interesting scene events [RKH∗ 09, SSSM14] that need to be vividly presented in the edited video. The objective critical for video editing and the key contribution of our work is to decide which shot (or rush) needs to be selected to describe each frame of the edited video. The shot selection problem is modeled as an optimization, which incorporates gaze information along with other cost terms that model cinematic editing principles. Gazed scene locations are utilized to define gaze potentials, which measure the importance of the different shots to choose from. Gaze potentials are then combined with other terms that model cinematic principles like avoiding jump cuts (which produce jarring shot transitions), rhythm (pace of shot transitioning), avoiding transient shots . The optimization is solved using dynamic programming. [MKSG20] refers to the detailed full article.

Abstract

Multi-object tracking has seen a lot of progress recently, albeit with substantial annotation costs for developing better and larger labeled datasets. In this work, we remove the need for annotated datasets by proposing an unsupervised re-identification network, thus sidestepping the labeling costs entirely, required for training. Given unlabeled videos, our proposed method (SimpleReID) first generates tracking labels using SORT [ 3] and trains a ReID network to predict the generated labels using crossentropy loss. We demonstrate that SimpleReID performs substantially better than simpler alternatives, and we recover the full performance of its supervised counterpart consistently across diverse tracking frameworks. The observations are unusual because unsupervised ReID is not expected to excel in crowded scenarios with occlusions, and drastic viewpoint changes. By incorporating our unsupervised SimpleReID with CenterTrack trained on augmented still images, we establish a new state-of-the-art performance on popular datasets like MOT16/17 without using tracking supervision, beating current best (CenterTrack) by 0.2-0.3 MOTA and 4.4-4.8 IDF1 scores. We further provide evidence for limited scope for improvement in IDF1 scores beyond our unsupervised ReID in the studied settings. Our investigation suggests reconsideration towards more sophisticated, supervised, end-to-end trackers [56 , 5] by showing promise in simpler unsupervised alternatives.

Abstract

In this paper, we propose the use of Message Sequence Charts (MSC) as a representation for visualizing narrative text in Hindi. An MSC is a formal representation allowing the depiction of actors and interactions among these actors in a scenario, apart from supporting a rich framework for formal inference. We propose an approach to extract MSC actors and interactions from a Hindi narrative. As a part of the approach, we enrich an existing event annotation scheme where we provide guidelines for annotation of the mood of events (realis vs irrealis) and guidelines for annotation of event arguments. We report performance on multiple evaluation criteria by experimenting with Hindi narratives from Indian History. Though Hindi is the fourth most-spoken first language in the world, from the NLP perspective it has comparatively lesser resources than English. Moreover, there is relatively less work in the context of event processing in Hindi. Hence, we believe that this work is among the initial works for Hindi event processing.

Abstract

Given the recent progress in language modeling using Transformer-based neural models and an active interest in generating stylized text, we present an approach to leverage the generalization capabilities of a language model to rewrite an input text in a target author’s style. Our proposed approach adapts a pre-trained language model to generate author-stylized text by fine-tuning on the author-specific corpus using a denoising autoencoder (DAE) loss in a cascaded encoder-decoder framework. Optimizing over DAE loss allows our model to learn the nuances of an author’s style without relying on parallel data, which has been a severe limitation of the previous related works in this space. To evaluate the efficacy of our approach, we propose a linguistically motivated framework to quantify stylistic alignment of the generated text to the target author at lexical, syntactic and surface levels. The evaluation framework is both interpretable as it leads to several insights about the model, and self-contained as it does not rely on external classifiers, e.g. sentiment or formality classifiers. Qualitative and quantitative assessment indicates that the proposed approach rewrites the input text with better alignment to the target style while preserving the original content better than state-of-the-art baselines.

Abstract

Episodic memories, when reactivated, can be modified or updated by new learning. Since such dynamic memory processes remain largely unexplored in psychiatric disorders, we examined the impact of depression on episodic memory updating. Unipolar and bipolar depression patients, and age/education matched controls, first learned a set of objects (List-1). Two days later, participants in all three groups were either reminded of the first learning session or not followed by the learning of a new set of objects (List-2). Forty-eight hours later, List-1 recall was impaired in unipolar and bipolar patients compared to control participants. Further, as expected, control participants who received a reminder spontaneously recalled items from List-2 during recall of List-1, indicative of an updated List-1 memory. Such spontaneous intrusions were also seen in the unipolar and bipolar patients that received the reminder, suggesting that memory pdating was unaffected in these two patient groups despite impaired recall of List 1. Unexpectedly, we observed a trend towards higher intrusions, albeit statistically insignificant, not only in the reminder but also in the no-reminder subgroups of bipolar patients. We probed this further in a second cohort by testing recall of List-2, which was also impaired in both depression groups. Again bipolar patients showed intrusions, but this time in the reverse order from List-1 into List-2, independent of a reminder. Taken together, despite impaired recall, updating of episodic memories was intact and unidirectional in unipolar depression. In contrast, indiscriminate updating, as evidenced by bidirectional interference between episodic memories, was seen in bipolar depression. These findings reveal a novel distinction between unipolar versus bipolar depression using a reactivation-dependent memory updating paradigm.

Abstract

Design of TFETs, with gate-drain underlap (Lun), exhibit suppressed off-state leakage and ambipolar conduction, thereby achieving larger on-to-off current ratio. In this work, through TCAD simulation study, we proposed an optimum value for gate-drain underlap length (Lun), and highlighted the advantages of designing TFETs with gate-drain underlap. Simulation framework was developed for both homojunction and heterojunction TFETs. The device design for both types of TFETs, considered similar doping profiles. The optimum value for Lun was determined to be half the gate length (Lg) from the DC characteristics, with little dependence of off-state leakage on the drain voltage. In the simulation study we also focused on the effect of the drain doping, and the gate length (Lg) on the performance of drain underlapped TFETs. The simulation study has been extensively performed on Ultra-Thin Body (UTB) III-V homojunction TFET and Ultra-Thin Body-Silicon On insulator (UTBSOI) Staggered gap (SG) III-V heterojunction TFET.

Abstract

Cinema Makes it Safe: Akaler Sandhane and the Problem of Looking This paper shall consider the trifecta of Bengali film directors Satyajit Ray (1921-1992), Mrinal Sen (1923-2018), and Ritwik Ghatak (1925-1976) to map a period in Indian film history when a political cinema was funded, at least in part, by the Indian government. The three directors were a provocative part of the Indian New Wave from the 1950s to the 1970s. They map two distinct definitions of “good political cinema” – from an aesthetically sophisticated cinema to a radical political text – that the state attempted to fund and administer in an attempt to develop cinema as an art form rather than as mass entertainment. In particular this paper shall consider Akaler Shandhaney (In Search of Famine, Sen, 1980) to argue that the film is unique in naming a pernicious relationship of inter-dependence between filmmaking, political speech, and the abject sub-altern. This self-reflexivity allows Sen to explore the exploitative nature of filmmaking and the middle class intellectual. Read in conjunction with Ashani Sanket (Distant Thunder, Ray 1973) and Jukti, Takko Aar Galpo (Reason, Story and Debate, Ghatak, 1977), Akaler Shandhaney calls into question filmmaking and funding practices, revealing the imbrication of national, social and cultural institutions in a complex interplay of aesthetic, ideological, and bureaucratic forces engaged in making “political” cinema possible. This paper argues that Sen uses this moment of self-reflexivity to speak a truth to the necessarily ambivalent and murky business of film making and viewing.

Abstract

Out of Censors: Netflix Original India and the Making of a New Normal This paper shall look three popular Netflix Original India productions Sacred Games (eriesS co-directed by Vikramaditya Motwane, Anurag Kashyap, 2018), Lust Stories (Anthology film co-directed by Anurag Kashyap, Dibakar Banerjee, Karan Johar, Zoya Akhtar, 2018) and Ghoul (Series directed by Patrick Graham, 2018). Each of the directors involved in these three productions have had run-ins with legal and extra-legal forms of censorship and moral policing in directing, producing, and marketing Hindi popular films. The relocation of cinema away from public screenings to the viewership afforded by Netflix has reterritorialized a new form of spectatorship. This allows these filmmakers to tell stories otherwise deemed too risky/risqué and attempt to re/claim a language of social and political critique. This paper shall consider the various strategies used by these immensely popular directors to argue that the relative freedom afforded by a global media-service provider unfettered by Indian legal regulation is mitigated by a language of co-optation. The three productions deal with police corruption, women’s sexuality, and Islamophobia and fascism respectively. All productions circulate in and acknowledge new globalities, changed sexual and power relations of image cultures and the traction afforded to a deterritorialized screening space. Yet these productions are bound by the exigencies of protecting and nurturing a particularly middle-class urban diasporic spectator from the vicissitudes of right-wing backlash on the one hand and an uncomfortable politics on the other.

Abstract

Software Requirement Specification documents provide natural language descriptions of the core functional requirements as a set of use-cases. Essentially, each use-case contains a set of actors and sequences of steps describing the interactions among them. Goals of use-case reviews and analyses include their correctness, completeness, detection of ambiguities, prototyping, verification, test case generation and traceability. Message Sequence Chart (MSC) have been proposed as a expressive, rigorous yet intuitive visual representation of use-cases. In this paper, we describe a linguistic knowledge-based approach to extract MSCs from use-cases. Compared to existing techniques, we extract richer constructs of the MSC notation such as timers, conditions and alt-boxes. We apply this tool to extract MSCs from several real-life software use-case descriptions and show that it performs better than the existing techniques. We also discuss the benefits and limitations of the extracted MSCs to meet the above goals.

Abstract

Integrating components of vehicular network with the Internet has emerged recently for fulfilling the ever-growing demand for a safe and comfortable driving experience. Road Side Unit (RSU) clouds help in serving requests arriving from vehicles but are limited by available resources. It is also required to reduce the overhead cost corresponding to Virtual Machine (VM) migrations caused by high mobility of vehicles. Also, requests need to be served within their stipulated delay constraint. In this work, we propose a novel algorithm to schedule requests at RSU clouds. Our algorithm efficiently schedules service requests from vehicles while taking care of their delay constraints and VM migrations. The simulation results confirm that our proposed scheduling technique helps in serving more number of requests within their stipulated delay constraint with lesser VM migrations.