Abstract

We present Ego-Exo4D, a diverse, large-scale multi- modal multiview video dataset and benchmark challenge. Ego-Exo4D centers around simultaneously-captured ego- centric and exocentric video of skilled human activities (e.g., sports, music, dance, bike repair). More than 800 participants from 13 cities worldwide performed these ac- tivities in 131 different natural scene contexts, yielding long-form captures from 1 to 42 minutes each and 1,422 hours of video combined. The multimodal nature of the dataset is unprecedented: the video is accompanied by mul- tichannel audio, eye gaze, 3D point clouds, camera poses, IMU, and multiplepaired language descriptions—including a novel “expert commentary” done by coaches and teach- ers and tailored to the skilled-activity domain. To push the frontier of first-person video understanding of skilled hu- man activity, we also present a suite of benchmark tasks and their annotations, including fine-grained activity un- derstanding, proficiency estimation, cross-view translation, and 3D hand/body pose. All resources will be open sourced to fuel new research in the community.

Abstract

We present Ego-Exo4D, a diverse, large-scale multi- modal multiview video dataset and benchmark challenge. Ego-Exo4D centers around simultaneously-captured ego- centric and exocentric video of skilled human activities (e.g., sports, music, dance, bike repair). More than 800 participants from 13 cities worldwide performed these ac- tivities in 131 different natural scene contexts, yielding long-form captures from 1 to 42 minutes each and 1,422 hours of video combined. The multimodal nature of the dataset is unprecedented: the video is accompanied by mul- tichannel audio, eye gaze, 3D point clouds, camera poses, IMU, and multiplepaired language descriptions—including a novel “expert commentary” done by coaches and teach- ers and tailored to the skilled-activity domain. To push the frontier of first-person video understanding of skilled hu- man activity, we also present a suite of benchmark tasks and their annotations, including fine-grained activity un- derstanding, proficiency estimation, cross-view translation, and 3D hand/body pose. All resources will be open sourced to fuel new research in the community

Abstract

iven multiple videos of the same task, procedure learn- ing addresses identifying the key-steps and determining their order to perform the task. For this purpose, existing approaches use the signal generated from a pair of videos. This makes key-steps discovery challenging as the algo- rithms lack inter-videos perspective. Instead, we propose an unsupervised Graph-based Procedure Learning (GPL) framework. GPL consists of the novel UnityGraph that rep- resents all the videos of a task as a graph to obtain both intra-video and inter-videos context. Further, to obtain sim- ilar embeddings for the same key-steps, the embeddings of UnityGraph are updated in an unsupervised manner using the Node2Vec algorithm. Finally, to identify the key-steps, we cluster the embeddings using KMeans. We test GPL on benchmark ProceL, CrossTask, and EgoProceL datasets and achieve an average improvement of 2% on third-person datasets and 3.6% on EgoProceL over the state-of-the-art.

Abstract

This work proposes the utilization of a self-supervised pre-trained network for developing a Language Identification (LID) system catering to low-resource Indian languages. The framework employed is Wav2vec2.0-XLSR-53, pre-trained on 53k hours of unlabeled speech data. The unsupervised training of the model enables it to learn the acoustic patterns specific to a language. Given that languages share phonetic space, multi-lingual pre-training is instrumental in learning cross-lingual information and building systems that cater to low-resource languages. Further fine-tuning with a limited amount of labeled data significantly boosts the model’s accuracy. The results showcase a relative improvement of 33.2% over the DNN-A (DNN with attention) model and 19.04% over Dense Resnets for the Language Identification task on the IIITH-ILSC database using the proposed features (Shivang Gupta and Kowshik Siva Sai Motepalli share first authorship).

Abstract

Analysis of Indian English (IE) pronunciation variabilities is useful in ASR and TTS modelling for the Indian context. Prior works characterised IE variabilities by reporting qualitative phonetic rules relative to Received Pronunciation (RP). However, such characterisations lack quantitative descriptors and data-driven analysis of diverse IE pronunciations, which could be due to the scarcity of phonetically labelled data. Furthermore, the versatility of IE stems from the influence of a large diversity of the speakers’ mother tongues and demographic region differences. To address these issues, we consider the corpus Indic TIMIT and manually obtain 13, 632 phonetic transcriptions in addition to those parts of the corpus. By performing a data-driven analysis on 15, 974 phonetic transcriptions of 80 speakers from diverse regions of India, we present a new set of phonetic rules and validate them against the existing phonetic rules to identify their relevance. Finally, we test the efficacy of Grapheme-to-Phoneme (G2P) conversion developed based on the obtained rules considering Phoneme Error Rate (PER) as the metric for performance.

Abstract

The global impact of coal mining and associated activities on land use/land cover (LULC) changes is significant. This study used Landsat satellite images from 1990 to 2020 to assess LULC changes and their impact on land surface temperature (LST) in four districts of Chhattisgarh state, India. Over three decades, Korba and Raigarh districts saw expansion in coal mines, built-up areas, and water bodies, while forest areas diminished by 711.3 km2 and 212.87 km2, respectively. Koriya district saw coal mine expansion of 5.68 km2 (1990–2010), later declining to 2.85 km2, alongside growth in built-up regions, and forest cover reduction by 251.31 km2 in 2020. Surguja district experienced coal mine and built-up area expansion (1990–2020), with initial forest decline of 160.21 km2 in 2010 followed by recovery in 2020. LST was determined using the Mono-window algorithm. LST increased during winter and summer, with the most significant rise in summer. Vegetation-rich regions had lower LST, while coal mines had the highest temperatures. There was a positive relationship between mining land patch size and patch temperatures. This study underscores the need for vegetation restoration in mining areas, particularly abandoned sites, and sustainable mining practices to mitigate coal mining's warming effects.

Abstract

Unconstrained Asian roads often involve poor infrastructure, affecting overall road safety. Missing traffic signs are a regular part of such roads. Missing or non-existing object detection has been studied for locating missing curbs and estimating reasonable regions for pedestrians on road scene images. Such methods involve analyzing task-specific single object cues. In this paper, we present the first and most challenging video dataset for missing objects, with multiple types of traffic signs for which the cues are visible without the signs in the scenes. We refer to it as the Missing Traffic Signs Video Dataset (MTSVD). MTSVD is challenging compared to the previous works in two aspects i) The traffic signs are generally not present in the vicinity of their cues, ii) The traffic signs’ cues are diverse and unique. Also, MTSVD is the first publicly available missing object dataset. To train the models for identifying missing signs, we complement our dataset with 10K traffic sign tracks, with 40% of the traffic signs having cues visible in the scenes. For identifying missing signs, we propose the Cue-driven Contextual Attention units (CueCAn), which we incorporate in our model’s encoder. We first train the encoder to classify the presence of traffic sign cues and then train the entire segmentation model end-to-end to localize missing traffic signs. Quantitative and qualitative analysis shows that CueCAn significantly improves the performance of base models.

Abstract

Large-scale deployment of fully autonomous vehicles re- quires a very high degree of robustness to unstructured traf- fic, weather conditions, and should prevent unsafe mispre- dictions. While there are several datasets and benchmarks focusing on segmentation for drive scenes, they are not specifically focused on safety and robustness issues. We introduce the IDD-AW dataset, which provides 5000 pairs of high-quality images with pixel-level annotations, cap- tured under rain, fog, low light, and snow in unstructured driving conditions. As compared to other adverse weather datasets, we provide i.) more annotated images, ii.) paired Near-Infrared (NIR) image for each frame, iii.) larger label set with a 4-level label hierarchy to capture unstructured traffic conditions. We benchmark state-of-the-art models for semantic segmentation in IDD-AW. We also propose a new metric called “Safe mean Intersection over Union (Safe mIoU)” for hierarchical datasets which penalizes danger- ous mispredictions that are not captured in the traditional definition of mean Intersection over Union (mIoU). The re- sults show that IDD-AW is one of the most challenging datasets to date for these tasks. The dataset and code will be available here: http://iddaw.github.io

Abstract

Researchers have extensively studied the field of vision and language, discovering that both visual and textual content is crucial for understanding scenes effectively. Particularly, comprehending text in videos holds great significance, requiring both scene text understanding and temporal reasoning. This paper focuses on exploring two recently introduced datasets, NewsVideoQA and M4-ViteVQA, which aim to address video question answering based on textual content. The NewsVideoQA dataset contains question-answer pairs related to the text in news videos, while M4-ViteVQA comprises question-answer pairs from diverse categories like vlogging, traveling, and shopping. We provide an analysis of the formulation of these datasets on various levels, exploring the degree of visual understanding and multi-frame comprehension required for answering the questions. Additionally, the study includes experimentation with BERT-QA, a text-only model, which demonstrates comparable performance to the original methods on both datasets, indicating the shortcomings in the formulation of these datasets. Furthermore, we also look into the domain adaptation aspect by examining the effectiveness of training on M4-ViteVQA and evaluating on NewsVideoQA and vice-versa, thereby shedding light on the challenges and potential benefits of out-of-domain training.

Abstract

Machine Learning models face increased concerns regarding the storage of personal user data and adverse impacts of corrupted data like backdoors or systematic bias. Machine Unlearning can address these by allowing post-hoc deletion of affected training data from a learned model. Achieving this task exactly is computationally expensive; consequently, recent works have proposed inexact unlearning algorithms to solve this approximately as well as evaluation methods to test the effectiveness of these algorithms. In this work, we first outline some necessary criteria for evaluation methods and show no existing evaluation satisfies them all. Then, we design a stronger black-box evaluation method called the Interclass Confusion (IC) test which adversarially manipulates data during training to detect the insufficiency of unlearning procedures. We also propose two analytically motivated baseline methods~(EU-k and CF-k) which outperform several popular inexact unlearning methods. Overall, we demonstrate how adversarial evaluation strategies can help in analyzing various unlearning phenomena which can guide the development of stronger unlearning algorithms.