The quality of the prompts provided to text-to-image diffusion models determines how faithful the generated content is to the user's intent, often requiring 'prompt engineering ‘. To harness visual concepts from target images without prompt engineering, current approaches largely rely on embedding inversion by optimizing and then mapping them to pseudo-tokens. However, working with such highdimensional vector representations is challenging because they lack semantics and interpretability, and only allow simple vector operations when using them. Instead, this work focuses on inverting the diffusion model to obtain interpretable language prompts directly. The challenge of doing this lies in the fact that the resulting optimization problem is fundamentally discrete and the space of prompts is exponentially large; this makes using standard optimization techniques, such as stochastic gradient descent, difficult. To this end, we utilize a delayed projection scheme to optimize for prompts representative of the vocabulary space in the model. Further, we leverage the findings that different timesteps of the diffusion process cater to different levels of detail in an image. The later, noisy, timesteps of the forward diffusion process correspond to the semantic information, and therefore, prompt inversion in this range provides tokens representative of the image semantics. We show that our approach can identify semantically interpretable and meaningful prompts for a target image which can be used to synthesize diverse images with similar content. We further illustrate the application of the optimized prompts in evolutionary image generation and concept removal.

There has been a recent explosion of impressive generative models that can produce high quality images (or videos) conditioned on text descriptions. However, all such approaches rely on conditional sentences that contain un-ambiguous descriptions of scenes and main actors in them. Therefore employing such models for more complex task of story visualization, where naturally references and co-references exist, and one requires to reason about when to maintain consistency of actors and backgrounds across frames/scenes, and when not to, based on story progression, remains a challenge. In this work, we address the aforementioned challenges and propose a novel autoregressive diffusion-based framework with a visual memory module that implicitly captures the actor and background context across the generated frames. Sentence-conditioned soft attention over the memories enables effective reference resolution and learns to maintain scene and actor consistency when needed. To validate the effectiveness of our approach, we extend the MUGEN dataset [19] and introduce additional characters, backgrounds and referencing in multi-sentence storylines. Our experiments for story generation on the MUGEN, the PororoSV [30] and the FlintstonesSV [16] dataset show that our method not only outperforms prior state-of-the-art in generating frames with high visual quality, which are consistent with the story, but also models appropriate correspondences between the characters and the background.

Learning how to localize and separate individual object sounds in the audio channel of the video is a difficult task. Current state-of-the-art methods predict audio masks from artificially mixed spectrograms, known as Mix-and-Separate framework. We propose an audio-visual co-segmentation, where the network learns both what individual objects look and sound like, from videos labeled with only object labels. Unlike other recent visually-guided audio source separation frameworks, our architecture can be learned in an end-to-end manner and requires no additional supervision or bounding box proposals. Specifically, we introduce weakly-supervised object segmentation in the context of sound separation. We also formulate spectrogram mask prediction using a set of learned mask bases, which combine using coefficients conditioned on the output of object segmentation — a design that facilitates separation. Extensive experiments on the MUSIC dataset show that our proposed approach outperforms state-of-the-art methods on visually guided sound source separation and sound denoising.

The recent success of transformer models in language, such as BERT, has motivated the use of such architectures for multi-modal feature learning and tasks. However, most multi-modal variants (e.g., ViLBERT) have limited themselves to visual-linguistic data. Relatively few have explored its use in audio-visual modalities, and none, to our knowledge, illustrate them in the context of granular audio-visual detection or segmentation tasks such as sound source separation and localization. In this work, we introduce TriBERT -- a transformer-based architecture, inspired by ViLBERT, which enables contextual feature learning across three modalities: vision, pose, and audio, with the use of flexible co-attention. The use of pose keypoints is inspired by recent works that illustrate that such representations can significantly boost performance in many audio-visual scenarios where often one or more persons are responsible for the sound explicitly (e.g., talking) or implicitly (e.g., sound produced as a function of human manipulating an object). From a technical perspective, as part of the TriBERT architecture, we introduce a learned visual tokenization scheme based on spatial attention and leverage weak-supervision to allow granular cross-modal interactions for visual and pose modalities. Further, we supplement learning with sound-source separation loss formulated across all three streams. We pre-train our model on the large MUSIC21 dataset and demonstrate improved performance in audio-visual sound source separation on that dataset as well as other datasets through fine-tuning. In addition, we show that the learned TriBERT representations are generic and significantly improve performance on other audio-visual tasks such as cross-modal audio-visual-pose retrieval by as much as 66.7% in top-1 accuracy.

We consider the problem of video-based person reidentification. The goal is to identify a person from videos captured under different cameras. In this paper, we propose an efficient attention based model for person re-identifying from videos. Our method generates an attention score for each frame based on frame-level features. The attention scores of all frames in a video are used to produce a weighted feature vector for the input video. This video-level feature vector is refined iteratively for re-identifying persons from videos. Unlike most existing deep learning methods that use global or spatial representation, our approach focuses on attention scores. Extensive experiments on three benchmark datasets demonstrate that our method achieves the state-of-the-art performance.

Given a video containing a person, the goal of person re-identification is to identify the same person from videos captured under different cameras. A common approach for tackling this problem is to first extract image features for all frames in the video. These frame-level features are then combined (e.g. via temporal pooling) to form a video-level feature vector. The video-level features of two input videos are then compared by calculating the distance between them. More recently, attention-based learning mechanism has been proposed for this problem. In particular, recurrent neural networks have been used to generate the attention scores of frames in a video. However, the limitation of RNN-based approach is that it is difficult for RNNs to capture long-range dependencies in videos. Inspired by the success of non-local neural networks, we propose a novel non-local temporal attention model in this paper. Our model can effectively capture long-range and global dependencies among the frames of the videos. Extensive experiments on three different benchmark datasets (i.e. iLIDS-VID, PRID-2011 and SDU-VID) show that our proposed method outperforms other state-of-the-art approaches.

Multi-modal learning, particularly among imaging and linguistic modalities, has made amazing strides in many high-level fundamental visual understanding problems, ranging from language grounding to dense event captioning. However, much of the research has been limited to approaches that either do not take audio corresponding to video into account at all, or those that model the audio-visual correlations in service of sound or sound source localization. In this paper, we present the evidence, that audio signals can carry surprising amount of information when it comes to high-level visual-lingual tasks. Specifically, we focus on the problem of weakly-supervised dense event captioning in videos and show that audio on its own can nearly rival performance of a state-of-the-art visual model and, combined with video, can improve on the state-of-the-art performance. Extensive experiments on the ActivityNet Captions dataset show that our proposed multi-modal approach outperforms state-of-the-art unimodal methods, as well as validate specific feature representation and architecture design choices.

The goal of video-based person re-identification is to match two input videos, so that the distance of the two videos is small if two videos contain the same person. A common approach for person re-identification is to first extract image features for all frames in the video, then aggregate all the features to form a video-level feature. The video-level features of two videos can then be used to calculate the distance of the two videos. In this paper, we propose a temporal attention approach for aggregating frame-level features into a video-level feature vector for re-identification. Our method is motivated by the fact that not all frames in a video are equally informative. We propose a fully convolutional temporal attention model for generating the attention scores. Fully convolutional network (FCN) has been widely used in semantic segmentation for generating 2D output maps. In this paper, we formulate video based person reidentification as a sequence labeling problem like semantic segmentation. We establish a connection between them and modify FCN to generate attention scores to represent the importance of each frame. Extensive experiments on three different benchmark datasets (i.e. iLIDS-VID, PRID-2011 and SDU-VID) show that our proposed method outperforms other state-of-the-art approaches.