The Pascal Visual Object Classes (VOC) challenge consists of two components: (i) a publicly available dataset of images together with ground truth annotation and standardised evaluation software; and (ii) an annual competition and workshop. There are five challenges: classification, detection, segmentation, action classification, and person layout. In this paper we provide a review of the challenge from 2008---2012. The paper is intended for two audiences: algorithm designers, researchers who want to see what the state of the art is, as measured by performance on the VOC datasets, along with the limitations and weak points of the current generation of algorithms; and, challenge designers, who want to see what we as organisers have learnt from the process and our recommendations for the organisation of future challenges. To analyse the performance of submitted algorithms on the VOC datasets we introduce a number of novel evaluation methods: a bootstrapping method for determining whether differences in the performance of two algorithms are significant or not; a normalised average precision so that performance can be compared across classes with different proportions of positive instances; a clustering method for visualising the performance across multiple algorithms so that the hard and easy images can be identified; and the use of a joint classifier over the submitted algorithms in order to measure their complementarity and combined performance. We also analyse the community's progress through time using the methods of Hoiem et al. (Proceedings of European Conference on Computer Vision, 2012) to identify the types of occurring errors. We conclude the paper with an appraisal of the aspects of the challenge that worked well, and those that could be improved in future challenges.

/pdf/the-pascal-visual-object-classes-challenge-a-retrospective-28ab0g4997.pdf

The Pascal Visual Object Classes Challenge: A Retrospective

Training a generic objectness measure to produce a small set of candidate object windows, has been shown to speed up the classical sliding window object detection paradigm. We observe that generic objects with well-defined closed boundary can be discriminated by looking at the norm of gradients, with a suitable resizing of their corresponding image windows in to a small fixed size. Based on this observation and computational reasons, we propose to resize the window to 8 × 8 and use the norm of the gradients as a simple 64D feature to describe it, for explicitly training a generic objectness measure. We further show how the binarized version of this feature, namely binarized normed gradients (BING), can be used for efficient objectness estimation, which requires only a few atomic operations (e.g. ADD, BITWISE SHIFT, etc.). Experiments on the challenging PASCAL VOC 2007 dataset show that our method efficiently (300fps on a single laptop CPU) generates a small set of category-independent, high quality object windows, yielding 96.2% object detection rate (DR) with 1, 000 proposals. Increasing the numbers of proposals and color spaces for computing BING features, our performance can be further improved to 99.5% DR.

/pdf/bing-binarized-normed-gradients-for-objectness-estimation-at-3g9kc2oxzc.pdf

BING: Binarized Normed Gradients for Objectness Estimation at 300fps

我的台灣, 看見心靈的故鄉 =2009林磐聳藝術與設計展

Learning text-video embeddings usually requires a dataset of video clips with manually provided captions. However, such datasets are expensive and time consuming to create and therefore difficult to obtain on a large scale. In this work, we propose instead to learn such embeddings from video data with readily available natural language annotations in the form of automatically transcribed narrations. The contributions of this work are three-fold. First, we introduce HowTo100M: a large-scale dataset of 136 million video clips sourced from 1.22M narrated instructional web videos depicting humans performing and describing over 23k different visual tasks. Our data collection procedure is fast, scalable and does not require any additional manual annotation. Second, we demonstrate that a text-video embedding trained on this data leads to state-of-the-art results for text-to-video retrieval and action localization on instructional video datasets such as YouCook2 or CrossTask. Finally, we show that this embedding transfers well to other domains: fine-tuning on generic Youtube videos (MSR-VTT dataset) and movies (LSMDC dataset) outperforms models trained on these datasets alone. Our dataset, code and models will be publicly available at: this http URL.

HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips

/pdf/wd-yt-brwndd-lmy-dnshgh-lwm-pzshkhy-khrdstn-brss-shkhshy-lm-1zmnwizalx.pdf

وضعیت برونداد علمی دانشگاه علوم پزشکی کردستان براساس شاخصهای علم سنجی تا پایان سال 2011 میلادی

The task of temporally detecting and segmenting actions in untrimmed videos has seen an increased attention recently. One problem in this context arises from the need to define and label action boundaries to create annotations for training which is very time and cost intensive. To address this issue, we propose an unsupervised approach for learning action classes from untrimmed video sequences. To this end, we use a continuous temporal embedding of framewise features to benefit from the sequential nature of activities. Based on the latent space created by the embedding, we identify clusters of temporal segments across all videos that correspond to semantic meaningful action classes. The approach is evaluated on three challenging datasets, namely the Breakfast dataset, YouTube Instructions, and the 50Salads dataset. While previous works assumed that the videos contain the same high level activity, we furthermore show that the proposed approach can also be applied to a more general setting where the content of the videos is unknown.

/pdf/unsupervised-learning-of-action-classes-with-continuous-407nxpeoyt.pdf

Unsupervised Learning of Action Classes With Continuous Temporal Embedding

This paper presents a new method for unsupervised segmentation of complex activities from video into multiple steps, or sub-activities, without any textual input. We propose an iterative discriminative-generative approach which alternates between discriminatively learning the appearance of sub-activities from the videos' visual features to sub-activity labels and generatively modelling the temporal structure of sub-activities using a Generalized Mallows Model. In addition, we introduce a model for background to account for frames unrelated to the actual activities. Our approach is validated on the challenging Breakfast Actions and Inria Instructional Videos datasets and outperforms both unsupervised and weakly-supervised state of the art.

Unsupervised Learning and Segmentation of Complex Activities from Video

How can we teach a robot to predict what will happen next for an activity it has never seen before? We address the problem of zero-shot anticipation by presenting a hierarchical model that generalizes instructional knowledge from large-scale text-corpora and transfers the knowledge to the visual domain. Given a portion of an instructional video, our model predicts coherent and plausible actions multiple steps into the future, all in rich natural language. To demonstrate the anticipation capabilities of our model, we introduce the Tasty Videos dataset, a collection of 2511 recipes for zero-shot learning, recognition and anticipation.

/pdf/zero-shot-anticipation-for-instructional-activities-3eabdwng2v.pdf

Zero-Shot Anticipation for Instructional Activities

Future prediction, especially in long-range videos, requires reasoning from current and past observations. In this work, we address questions of temporal extent, scaling, and level of semantic abstraction with a flexible multi-granular temporal aggregation framework. We show that it is possible to achieve state of the art in both next action and dense anticipation with simple techniques such as max-pooling and attention. To demonstrate the anticipation capabilities of our model, we conduct experiments on Breakfast, 50Salads, and EPIC-Kitchens datasets, where we achieve state-of-the-art results. With minimal modifications, our model can also be extended for video segmentation and action recognition.

Temporal Aggregate Representations for Long-Range Video Understanding

We propose a multi-cue based approach for recognizing human actions in still images, where relevant object regions are discovered and utilized in a weakly supervised manner. Our approach does not require any explicitly trained object detector or part/attribute annotation. Instead, a multiple instance learning approach is used over sets of object hypotheses in order to represent objects relevant to the actions. We test our method on the extensive Stanford 40 Actions dataset [1] and achieve significant performance gain compared to the state-of-the-art. Our results show that using multiple object hypotheses within multiple instance learning is effective for human action recognition in still images and such an object representation is suitable for using in conjunction with other visual features.

/pdf/on-recognizing-actions-in-still-images-via-multiple-features-106ch4uzlx.pdf

Fadime Sener

Papers

Unsupervised Learning of Action Classes With Continuous Temporal Embedding

Unsupervised Learning and Segmentation of Complex Activities from Video

Zero-Shot Anticipation for Instructional Activities

Temporal Aggregate Representations for Long-Range Video Understanding

On recognizing actions in still images via multiple features