Learned video compression methods have gained a variety of interest in the video coding community since they have matched or even exceeded the rate-distortion (RD) performance of traditional video codecs. However, many current learning-based methods are dedicated to utilizing short-range temporal information, thus limiting their performance. In this paper, we focus on exploiting the unique characteristics of video content and further exploring temporal information to enhance compression performance. Specifically, for long-range temporal information exploitation, we propose temporal prior that can update continuously within the group of pictures (GOP) during inference. In that case temporal prior contains valuable temporal information of all decoded images within the current GOP. As for short-range temporal information, we propose a progressive guided motion compensation to achieve robust and effective compensation. In detail, we design a hierarchical structure to achieve multi-scale compensation. More importantly, we use optical flow guidance to generate pixel offsets between feature maps at each scale, and the compensation results at each scale will be used to guide the following scale's compensation. Sufficient experimental results demonstrate that our method can obtain better RD performance than state-of-the-art video compression approaches. The code is publicly available on: //github.com/Huairui/LSTVC.
相關內容
Consecutive frames in a video contain redundancy, but they may also contain relevant complementary information for the detection task. The objective of our work is to leverage this complementary information to improve detection. Therefore, we propose a spatio-temporal fusion framework (STF). We first introduce multi-frame and single-frame attention modules that allow a neural network to share feature maps between nearby frames to obtain more robust object representations. Second, we introduce a dual-frame fusion module that merges feature maps in a learnable manner to improve them. Our evaluation is conducted on three different benchmarks including video sequences of moving road users. The performed experiments demonstrate that the proposed spatio-temporal fusion module leads to improved detection performance compared to baseline object detectors. Code is available at //github.com/noreenanwar/STF-module
We present Q-ViD, a simple approach for video question answering (video QA), that unlike prior methods, which are based on complex architectures, computationally expensive pipelines or use closed models like GPTs, Q-ViD relies on a single instruction-aware open vision-language model (InstructBLIP) to tackle videoQA using frame descriptions. Specifically, we create captioning instruction prompts that rely on the target questions about the videos and leverage InstructBLIP to obtain video frame captions that are useful to the task at hand. Subsequently, we form descriptions of the whole video using the question-dependent frame captions, and feed that information, along with a question-answering prompt, to a large language model (LLM). The LLM is our reasoning module, and performs the final step of multiple-choice QA. Our simple Q-ViD framework achieves competitive or even higher performances than current state of the art models on a diverse range of videoQA benchmarks, including NExT-QA, STAR, How2QA, TVQA and IntentQA.
Short videos on platforms such as TikTok, Instagram Reels, and YouTube Shorts (i.e. short-form videos) have become a primary source of information and entertainment. Many short-form videos are inaccessible to blind and low vision (BLV) viewers due to their rapid visual changes, on-screen text, and music or meme-audio overlays. In our formative study, 7 BLV viewers who regularly watched short-form videos reported frequently skipping such inaccessible content. We present ShortScribe, a system that provides hierarchical visual summaries of short-form videos at three levels of detail to support BLV viewers in selecting and understanding short-form videos. ShortScribe allows BLV users to navigate between video descriptions based on their level of interest. To evaluate ShortScribe, we assessed description accuracy and conducted a user study with 10 BLV participants comparing ShortScribe to a baseline interface. When using ShortScribe, participants reported higher comprehension and provided more accurate summaries of video content.
Recent state-of-the-art semi-supervised Video Object Segmentation (VOS) methods have shown significant improvements in target object segmentation accuracy when information from preceding frames is used in segmenting the current frame. In particular, such memory-based approaches can help a model to more effectively handle appearance changes (representation drift) or occlusions. Ideally, for maximum performance, Online VOS methods would need all or most of the preceding frames (or their extracted information) to be stored in memory and be used for online learning in later frames. Such a solution is not feasible for long videos, as the required memory size grows without bound, and such methods can fail when memory is limited and a target object experiences repeated representation drifts throughout a video. We propose two novel techniques to reduce the memory requirement of Online VOS methods while improving modeling accuracy and generalization on long videos. Motivated by the success of continual learning techniques in preserving previously-learned knowledge, here we propose Gated-Regularizer Continual Learning (GRCL), which improves the performance of any Online VOS subject to limited memory, and a Reconstruction-based Memory Selection Continual Learning (RMSCL), which empowers Online VOS methods to efficiently benefit from stored information in memory. We also analyze the performance of a hybrid combination of the two proposed methods. Experimental results show that the proposed methods are able to improve the performance of Online VOS models by more than 8%, with improved robustness on long-video datasets while maintaining comparable performance on short-video datasets such as DAVIS16, DAVIS17, and YouTube-VOS18.
In endoscopic imaging, the recorded images are prone to exposure abnormalities, so maintaining high-quality images is important to assist healthcare professionals in performing decision-making. To overcome this issue, We design a frequency-domain based network, called FD-Vision Mamba (FDVM-Net), which achieves high-quality image exposure correction by reconstructing the frequency domain of endoscopic images. Specifically, inspired by the State Space Sequence Models (SSMs), we develop a C-SSM block that integrates the local feature extraction ability of the convolutional layer with the ability of the SSM to capture long-range dependencies. A two-path network is built using C-SSM as the basic function cell, and these two paths deal with the phase and amplitude information of the image, respectively. Finally, a degraded endoscopic image is reconstructed by FDVM-Net to obtain a high-quality clear image. Extensive experimental results demonstrate that our method achieves state-of-the-art results in terms of speed and accuracy, and it is noteworthy that our method can enhance endoscopic images of arbitrary resolution. The URL of the code is \url{//github.com/zzr-idam/FDVM-Net}.
Convolutional neural networks (CNNs) have shown dramatic improvements in single image super-resolution (SISR) by using large-scale external samples. Despite their remarkable performance based on the external dataset, they cannot exploit internal information within a specific image. Another problem is that they are applicable only to the specific condition of data that they are supervised. For instance, the low-resolution (LR) image should be a "bicubic" downsampled noise-free image from a high-resolution (HR) one. To address both issues, zero-shot super-resolution (ZSSR) has been proposed for flexible internal learning. However, they require thousands of gradient updates, i.e., long inference time. In this paper, we present Meta-Transfer Learning for Zero-Shot Super-Resolution (MZSR), which leverages ZSSR. Precisely, it is based on finding a generic initial parameter that is suitable for internal learning. Thus, we can exploit both external and internal information, where one single gradient update can yield quite considerable results. (See Figure 1). With our method, the network can quickly adapt to a given image condition. In this respect, our method can be applied to a large spectrum of image conditions within a fast adaptation process.
Image-to-image translation aims to learn the mapping between two visual domains. There are two main challenges for many applications: 1) the lack of aligned training pairs and 2) multiple possible outputs from a single input image. In this work, we present an approach based on disentangled representation for producing diverse outputs without paired training images. To achieve diversity, we propose to embed images onto two spaces: a domain-invariant content space capturing shared information across domains and a domain-specific attribute space. Our model takes the encoded content features extracted from a given input and the attribute vectors sampled from the attribute space to produce diverse outputs at test time. To handle unpaired training data, we introduce a novel cross-cycle consistency loss based on disentangled representations. Qualitative results show that our model can generate diverse and realistic images on a wide range of tasks without paired training data. For quantitative comparisons, we measure realism with user study and diversity with a perceptual distance metric. We apply the proposed model to domain adaptation and show competitive performance when compared to the state-of-the-art on the MNIST-M and the LineMod datasets.
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.
Top-down visual attention mechanisms have been used extensively in image captioning and visual question answering (VQA) to enable deeper image understanding through fine-grained analysis and even multiple steps of reasoning. In this work, we propose a combined bottom-up and top-down attention mechanism that enables attention to be calculated at the level of objects and other salient image regions. This is the natural basis for attention to be considered. Within our approach, the bottom-up mechanism (based on Faster R-CNN) proposes image regions, each with an associated feature vector, while the top-down mechanism determines feature weightings. Applying this approach to image captioning, our results on the MSCOCO test server establish a new state-of-the-art for the task, achieving CIDEr / SPICE / BLEU-4 scores of 117.9, 21.5 and 36.9, respectively. Demonstrating the broad applicability of the method, applying the same approach to VQA we obtain first place in the 2017 VQA Challenge.
While existing machine learning models have achieved great success for sentiment classification, they typically do not explicitly capture sentiment-oriented word interaction, which can lead to poor results for fine-grained analysis at the snippet level (a phrase or sentence). Factorization Machine provides a possible approach to learning element-wise interaction for recommender systems, but they are not directly applicable to our task due to the inability to model contexts and word sequences. In this work, we develop two Position-aware Factorization Machines which consider word interaction, context and position information. Such information is jointly encoded in a set of sentiment-oriented word interaction vectors. Compared to traditional word embeddings, SWI vectors explicitly capture sentiment-oriented word interaction and simplify the parameter learning. Experimental results show that while they have comparable performance with state-of-the-art methods for document-level classification, they benefit the snippet/sentence-level sentiment analysis.
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