The success of deep learning models has led to their adaptation and adoption by prominent video understanding methods. The majority of these approaches encode features in a joint space-time modality for which the inner workings and learned representations are difficult to visually interpret. We propose LEArned Preconscious Synthesis (LEAPS), an architecture-agnostic method for synthesizing videos from the internal spatiotemporal representations of models. Using a stimulus video and a target class, we prime a fixed space-time model and iteratively optimize a video initialized with random noise. We incorporate additional regularizers to improve the feature diversity of the synthesized videos as well as the cross-frame temporal coherence of motions. We quantitatively and qualitatively evaluate the applicability of LEAPS by inverting a range of spatiotemporal convolutional and attention-based architectures trained on Kinetics-400, which to the best of our knowledge has not been previously accomplished.
相關內容
Large-scale text-to-video diffusion models have demonstrated an exceptional ability to synthesize diverse videos. However, due to the lack of extensive text-to-video datasets and the necessary computational resources for training, directly applying these models for video stylization remains difficult. Also, given that the noise addition process on the input content is random and destructive, fulfilling the style transfer task's content preservation criteria is challenging. This paper proposes a zero-shot video stylization method named Style-A-Video, which utilizes a generative pre-trained transformer with an image latent diffusion model to achieve a concise text-controlled video stylization. We improve the guidance condition in the denoising process, establishing a balance between artistic expression and structure preservation. Furthermore, to decrease inter-frame flicker and avoid the formation of additional artifacts, we employ a sampling optimization and a temporal consistency module. Extensive experiments show that we can attain superior content preservation and stylistic performance while incurring less consumption than previous solutions. Code will be available at //github.com/haha-lisa/Style-A-Video.
Graph neural networks (GNNs), a type of neural network that can learn from graph-structured data and learn the representation of nodes by aggregating their neighbors, have shown excellent performance in downstream tasks.However, it is known that the performance of graph neural networks (GNNs) degrades gradually as the number of layers increases. Based on k-hop subgraph aggregation, which is a new concept, we propose a new perspective to understand the expressive power of GNN.From this perspective, we reveal the potential causes of the performance degradation of the deep traditional GNN - aggregated subgraph overlap, and the fact that the residual-based graph neural networks in fact exploit the aggregation results of 1 to k hop subgraphs to improve the effectiveness.Further, we propose a new sampling-based node-level residual module named SDF, which is shown by theoretical derivation to obtain a superior expressive power compared to previous residual methods by using information from 1 to k hop subgraphs more flexibly. Extensive experiments show that the performance and efficiency of GNN with the SDF module outperform other methods.
Accurate time series forecasting is a fundamental challenge in data science. It is often affected by external covariates such as weather or human intervention, which in many applications, may be predicted with reasonable accuracy. We refer to them as predicted future covariates. However, existing methods that attempt to predict time series in an iterative manner with autoregressive models end up with exponential error accumulations. Other strategies hat consider the past and future in the encoder and decoder respectively limit themselves by dealing with the historical and future data separately. To address these limitations, a novel feature representation strategy -- shifting -- is proposed to fuse the past data and future covariates such that their interactions can be considered. To extract complex dynamics in time series, we develop a parallel deep learning framework composed of RNN and CNN, both of which are used hierarchically. We also utilize the skip connection technique to improve the model's performance. Extensive experiments on three datasets reveal the effectiveness of our method. Finally, we demonstrate the model interpretability using the Grad-CAM algorithm.
In this work, we are dedicated to leveraging the denoising diffusion models' success and formulating feature refinement as the autoencoder-formed diffusion process. The state-of-the-art CSLR framework consists of a spatial module, a visual module, a sequence module, and a sequence learning function. However, this framework has faced sequence module overfitting caused by the objective function and small-scale available benchmarks, resulting in insufficient model training. To overcome the overfitting problem, some CSLR studies enforce the sequence module to learn more visual temporal information or be guided by more informative supervision to refine its representations. In this work, we propose a novel autoencoder-formed conditional diffusion feature refinement~(ACDR) to refine the sequence representations to equip desired properties by learning the encoding-decoding optimization process in an end-to-end way. Specifically, for the ACDR, a noising Encoder is proposed to progressively add noise equipped with semantic conditions to the sequence representations. And a denoising Decoder is proposed to progressively denoise the noisy sequence representations with semantic conditions. Therefore, the sequence representations can be imbued with the semantics of provided semantic conditions. Further, a semantic constraint is employed to prevent the denoised sequence representations from semantic corruption. Extensive experiments are conducted to validate the effectiveness of our ACDR, benefiting state-of-the-art methods and achieving a notable gain on three benchmarks.
Vision-and-Language Navigation (VLN) is a realistic but challenging task that requires an agent to locate the target region using verbal and visual cues. While significant advancements have been achieved recently, there are still two broad limitations: (1) The explicit information mining for significant guiding semantics concealed in both vision and language is still under-explored; (2) The previously structured map method provides the average historical appearance of visited nodes, while it ignores distinctive contributions of various images and potent information retention in the reasoning process. This work proposes a dual semantic-aware recurrent global-adaptive network (DSRG) to address the above problems. First, DSRG proposes an instruction-guidance linguistic module (IGL) and an appearance-semantics visual module (ASV) for boosting vision and language semantic learning respectively. For the memory mechanism, a global adaptive aggregation module (GAA) is devised for explicit panoramic observation fusion, and a recurrent memory fusion module (RMF) is introduced to supply implicit temporal hidden states. Extensive experimental results on the R2R and REVERIE datasets demonstrate that our method achieves better performance than existing methods.
Image-based rendering techniques stand at the core of an immersive experience for the user, as they generate novel views given a set of multiple input images. Since they have shown good performance in terms of objective and subjective quality, the research community devotes great effort to their improvement. However, the large volume of data necessary to render at the receiver's side hinders applications in limited bandwidth environments or prevents their employment in real-time applications. We present LeHoPP, a method for input pixel pruning, where we examine the importance of each input pixel concerning the rendered view, and we avoid the use of irrelevant pixels. Even without retraining the image-based rendering network, our approach shows a good trade-off between synthesis quality and pixel rate. When tested in the general neural rendering framework, compared to other pruning baselines, LeHoPP gains between $0.9$ dB and $3.6$ dB on average.
We present DreamPose, a diffusion-based method for generating animated fashion videos from still images. Given an image and a sequence of human body poses, our method synthesizes a video containing both human and fabric motion. To achieve this, we transform a pretrained text-to-image model (Stable Diffusion) into a pose-and-image guided video synthesis model, using a novel finetuning strategy, a set of architectural changes to support the added conditioning signals, and techniques to encourage temporal consistency. We fine-tune on a collection of fashion videos from the UBC Fashion dataset. We evaluate our method on a variety of clothing styles and poses, and demonstrate that our method produces state-of-the-art results on fashion video animation. Video results are available on our project page.
Spatio-temporal representation learning is critical for video self-supervised representation. Recent approaches mainly use contrastive learning and pretext tasks. However, these approaches learn representation by discriminating sampled instances via feature similarity in the latent space while ignoring the intermediate state of the learned representations, which limits the overall performance. In this work, taking into account the degree of similarity of sampled instances as the intermediate state, we propose a novel pretext task - spatio-temporal overlap rate (STOR) prediction. It stems from the observation that humans are capable of discriminating the overlap rates of videos in space and time. This task encourages the model to discriminate the STOR of two generated samples to learn the representations. Moreover, we employ a joint optimization combining pretext tasks with contrastive learning to further enhance the spatio-temporal representation learning. We also study the mutual influence of each component in the proposed scheme. Extensive experiments demonstrate that our proposed STOR task can favor both contrastive learning and pretext tasks. The joint optimization scheme can significantly improve the spatio-temporal representation in video understanding. The code is available at //github.com/Katou2/CSTP.
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.
Recently, deep learning has achieved very promising results in visual object tracking. Deep neural networks in existing tracking methods require a lot of training data to learn a large number of parameters. However, training data is not sufficient for visual object tracking as annotations of a target object are only available in the first frame of a test sequence. In this paper, we propose to learn hierarchical features for visual object tracking by using tree structure based Recursive Neural Networks (RNN), which have fewer parameters than other deep neural networks, e.g. Convolutional Neural Networks (CNN). First, we learn RNN parameters to discriminate between the target object and background in the first frame of a test sequence. Tree structure over local patches of an exemplar region is randomly generated by using a bottom-up greedy search strategy. Given the learned RNN parameters, we create two dictionaries regarding target regions and corresponding local patches based on the learned hierarchical features from both top and leaf nodes of multiple random trees. In each of the subsequent frames, we conduct sparse dictionary coding on all candidates to select the best candidate as the new target location. In addition, we online update two dictionaries to handle appearance changes of target objects. Experimental results demonstrate that our feature learning algorithm can significantly improve tracking performance on benchmark datasets.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191