We propose a method to detect individualized highlights for users on given target videos based on their preferred highlight clips marked on previous videos they have watched. Our method explicitly leverages the contents of both the preferred clips and the target videos using pre-trained features for the objects and the human activities. We design a multi-head attention mechanism to adaptively weigh the preferred clips based on their object- and human-activity-based contents, and fuse them using these weights into a single feature representation for each user. We compute similarities between these per-user feature representations and the per-frame features computed from the desired target videos to estimate the user-specific highlight clips from the target videos. We test our method on a large-scale highlight detection dataset containing the annotated highlights of individual users. Compared to current baselines, we observe an absolute improvement of 2-4% in the mean average precision of the detected highlights. We also perform extensive ablation experiments on the number of preferred highlight clips associated with each user as well as on the object- and human-activity-based feature representations to validate that our method is indeed both content-based and user-specific.
相關內容
While transformers have begun to dominate many tasks in vision, applying them to large images is still computationally difficult. A large reason for this is that self-attention scales quadratically with the number of tokens, which in turn, scales quadratically with the image size. On larger images (e.g., 1080p), over 60% of the total computation in the network is spent solely on creating and applying attention matrices. We take a step toward solving this issue by introducing Hydra Attention, an extremely efficient attention operation for Vision Transformers (ViTs). Paradoxically, this efficiency comes from taking multi-head attention to its extreme: by using as many attention heads as there are features, Hydra Attention is computationally linear in both tokens and features with no hidden constants, making it significantly faster than standard self-attention in an off-the-shelf ViT-B/16 by a factor of the token count. Moreover, Hydra Attention retains high accuracy on ImageNet and, in some cases, actually improves it.
Audio-visual automatic speech recognition (AV-ASR) extends speech recognition by introducing the video modality as an additional source of information. In this work, the information contained in the motion of the speaker's mouth is used to augment the audio features. The video modality is traditionally processed with a 3D convolutional neural network (e.g. 3D version of VGG). Recently, image transformer networks arXiv:2010.11929 demonstrated the ability to extract rich visual features for image classification tasks. Here, we propose to replace the 3D convolution with a video transformer to extract visual features. We train our baselines and the proposed model on a large scale corpus of YouTube videos. The performance of our approach is evaluated on a labeled subset of YouTube videos as well as on the LRS3-TED public corpus. Our best video-only model obtains 34.9% WER on YTDEV18 and 19.3% on LRS3-TED, a 10% and 9% relative improvements over our convolutional baseline. We achieve the state of the art performance of the audio-visual recognition on the LRS3-TED after fine-tuning our model (1.6% WER). In addition, in a series of experiments on multi-person AV-ASR, we obtained an average relative reduction of 2% WER over our convolutional video frontend.
Video highlights detection has been long researched as a topic in computer vision tasks, digging the user-appealing clips out given unexposed raw video inputs. However, in most case, the mainstream methods in this line of research are built on the closed world assumption, where a fixed number of highlight categories is defined properly in advance and need all training data to be available at the same time, and as a result, leads to poor scalability with respect to both the highlight categories and the size of the dataset. To tackle the problem mentioned above, we propose a video highlights detector that is able to learn incrementally, namely \textbf{G}lobal \textbf{P}rototype \textbf{E}ncoding (GPE), capturing newly defined video highlights in the extended dataset via their corresponding prototypes. Alongside, we present a well annotated and costly dataset termed \emph{ByteFood}, including more than 5.1k gourmet videos belongs to four different domains which are \emph{cooking}, \emph{eating}, \emph{food material}, and \emph{presentation} respectively. To the best of our knowledge, this is the first time the incremental learning settings are introduced to video highlights detection, which in turn relieves the burden of training video inputs and promotes the scalability of conventional neural networks in proportion to both the size of the dataset and the quantity of domains. Moreover, the proposed GPE surpasses current incremental learning methods on \emph{ByteFood}, reporting an improvement of 1.57\% mAP at least. The code and dataset will be made available sooner.
Recent deep learning approaches for multi-view depth estimation are employed either in a depth-from-video or a multi-view stereo setting. Despite different settings, these approaches are technically similar: they correlate multiple source views with a keyview to estimate a depth map for the keyview. In this work, we introduce the Robust Multi-View Depth Benchmark that is built upon a set of public datasets and allows evaluation in both settings on data from different domains. We evaluate recent approaches and find imbalanced performances across domains. Further, we consider a third setting, where camera poses are available and the objective is to estimate the corresponding depth maps with their correct scale. We show that recent approaches do not generalize across datasets in this setting. This is because their cost volume output runs out of distribution. To resolve this, we present the Robust MVD Baseline model for multi-view depth estimation, which is built upon existing components but employs a novel scale augmentation procedure. It can be applied for robust multi-view depth estimation, independent of the target data. We provide code for the proposed benchmark and baseline model at //github.com/lmb-freiburg/robustmvd.
Attention layers are an integral part of modern end-to-end automatic speech recognition systems, for instance as part of the Transformer or Conformer architecture. Attention is typically multi-headed, where each head has an independent set of learned parameters and operates on the same input feature sequence. The output of multi-headed attention is a fusion of the outputs from the individual heads. We empirically analyze the diversity between representations produced by the different attention heads and demonstrate that the heads become highly correlated during the course of training. We investigate a few approaches to increasing attention head diversity, including using different attention mechanisms for each head and auxiliary training loss functions to promote head diversity. We show that introducing diversity-promoting auxiliary loss functions during training is a more effective approach, and obtain WER improvements of up to 6% relative on the Librispeech corpus. Finally, we draw a connection between the diversity of attention heads and the similarity of the gradients of head parameters.
Annotating bounding boxes for object detection is expensive, time-consuming, and error-prone. In this work, we propose a DETR based framework called ComplETR that is designed to explicitly complete missing annotations in partially annotated dense scene datasets. This reduces the need to annotate every object instance in the scene thereby reducing annotation cost. ComplETR augments object queries in DETR decoder with patch information of objects in the image. Combined with a matching loss, it can effectively find objects that are similar to the input patch and complete the missing annotations. We show that our framework outperforms the state-of-the-art methods such as Soft Sampling and Unbiased Teacher by itself, while at the same time can be used in conjunction with these methods to further improve their performance. Our framework is also agnostic to the choice of the downstream object detectors; we show performance improvement for several popular detectors such as Faster R-CNN, Cascade R-CNN, CenterNet2, and Deformable DETR on multiple dense scene datasets.
Transformer, an attention-based encoder-decoder architecture, has revolutionized the field of natural language processing. Inspired by this significant achievement, some pioneering works have recently been done on adapting Transformerliked architectures to Computer Vision (CV) fields, which have demonstrated their effectiveness on various CV tasks. Relying on competitive modeling capability, visual Transformers have achieved impressive performance on multiple benchmarks such as ImageNet, COCO, and ADE20k as compared with modern Convolution Neural Networks (CNN). In this paper, we have provided a comprehensive review of over one hundred different visual Transformers for three fundamental CV tasks (classification, detection, and segmentation), where a taxonomy is proposed to organize these methods according to their motivations, structures, and usage scenarios. Because of the differences in training settings and oriented tasks, we have also evaluated these methods on different configurations for easy and intuitive comparison instead of only various benchmarks. Furthermore, we have revealed a series of essential but unexploited aspects that may empower Transformer to stand out from numerous architectures, e.g., slack high-level semantic embeddings to bridge the gap between visual and sequential Transformers. Finally, three promising future research directions are suggested for further investment.
We present a novel counterfactual framework for both Zero-Shot Learning (ZSL) and Open-Set Recognition (OSR), whose common challenge is generalizing to the unseen-classes by only training on the seen-classes. Our idea stems from the observation that the generated samples for unseen-classes are often out of the true distribution, which causes severe recognition rate imbalance between the seen-class (high) and unseen-class (low). We show that the key reason is that the generation is not Counterfactual Faithful, and thus we propose a faithful one, whose generation is from the sample-specific counterfactual question: What would the sample look like, if we set its class attribute to a certain class, while keeping its sample attribute unchanged? Thanks to the faithfulness, we can apply the Consistency Rule to perform unseen/seen binary classification, by asking: Would its counterfactual still look like itself? If ``yes'', the sample is from a certain class, and ``no'' otherwise. Through extensive experiments on ZSL and OSR, we demonstrate that our framework effectively mitigates the seen/unseen imbalance and hence significantly improves the overall performance. Note that this framework is orthogonal to existing methods, thus, it can serve as a new baseline to evaluate how ZSL/OSR models generalize. Codes are available at //github.com/yue-zhongqi/gcm-cf.
Contextual word representations derived from pre-trained bidirectional language models (biLMs) have recently been shown to provide significant improvements to the state of the art for a wide range of NLP tasks. However, many questions remain as to how and why these models are so effective. In this paper, we present a detailed empirical study of how the choice of neural architecture (e.g. LSTM, CNN, or self attention) influences both end task accuracy and qualitative properties of the representations that are learned. We show there is a tradeoff between speed and accuracy, but all architectures learn high quality contextual representations that outperform word embeddings for four challenging NLP tasks. Additionally, all architectures learn representations that vary with network depth, from exclusively morphological based at the word embedding layer through local syntax based in the lower contextual layers to longer range semantics such coreference at the upper layers. Together, these results suggest that unsupervised biLMs, independent of architecture, are learning much more about the structure of language than previously appreciated.
Dense video captioning aims to generate text descriptions for all events in an untrimmed video. This involves both detecting and describing events. Therefore, all previous methods on dense video captioning tackle this problem by building two models, i.e. an event proposal and a captioning model, for these two sub-problems. The models are either trained separately or in alternation. This prevents direct influence of the language description to the event proposal, which is important for generating accurate descriptions. To address this problem, we propose an end-to-end transformer model for dense video captioning. The encoder encodes the video into appropriate representations. The proposal decoder decodes from the encoding with different anchors to form video event proposals. The captioning decoder employs a masking network to restrict its attention to the proposal event over the encoding feature. This masking network converts the event proposal to a differentiable mask, which ensures the consistency between the proposal and captioning during training. In addition, our model employs a self-attention mechanism, which enables the use of efficient non-recurrent structure during encoding and leads to performance improvements. We demonstrate the effectiveness of this end-to-end model on ActivityNet Captions and YouCookII datasets, where we achieved 10.12 and 6.58 METEOR score, respectively.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191