Visual prompt, a pair of before-and-after edited images, can convey indescribable imagery transformations and prosper in image editing. However, current visual prompt methods rely on a pretrained text-guided image-to-image generative model that requires a triplet of text, before, and after images for retraining over a text-to-image model. Such crafting triplets and retraining processes limit the scalability and generalization of editing. In this paper, we present a framework based on any single text-to-image model without reliance on the explicit image-to-image model thus enhancing the generalizability and scalability. Specifically, by leveraging the probability-flow ordinary equation, we construct a diffusion bridge to transfer the distribution between before-and-after images under the text guidance. By optimizing the text via the bridge, the framework adaptively textualizes the editing transformation conveyed by visual prompts into text embeddings without other models. Meanwhile, we introduce differential attention control during optimization, which disentangles the text embedding from the invariance of the before-and-after images and makes it solely capture the delicate transformation and generalize to edit various images. Experiments on real images validate competitive results on the generalization, contextual coherence, and high fidelity for delicate editing with just one image pair as the visual prompt.

Detecting segments of interest from videos is a common problem for many applications. And yet it is a challenging problem as it often requires not only knowledge of individual target segments, but also contextual understanding of the entire video and the relationships between the target segments. To address this problem, we propose the Sequence-to-Segments Network (S2N), a novel and general end-to-end sequential encoder-decoder architecture. S2N first encodes the input video into a sequence of hidden states that capture information progressively, as it appears in the video. It then employs the Segment Detection Unit (SDU), a novel decoding architecture, that sequentially detects segments. At each decoding step, the SDU integrates the decoder state and encoder hidden states to detect a target segment. During training, we address the problem of finding the best assignment of predicted segments to ground truth using the Hungarian Matching Algorithm with Lexicographic Cost. Additionally we propose to use the squared Earth Mover's Distance to optimize the localization errors of the segments. We show the state-of-the-art performance of S2N across numerous tasks, including video highlighting, video summarization, and human action proposal generation.

Existing interactive visualization tools for deep learning are mostly applied to the training, debugging, and refinement of neural network models working on natural images. However, visual analytics tools are lacking for the specific application of x-ray image classification with multiple structural attributes. In this paper, we present an interactive system for domain scientists to visually study the multiple attributes learning models applied to x-ray scattering images. It allows domain scientists to interactively explore this important type of scientific images in embedded spaces that are defined on the model prediction output, the actual labels, and the discovered feature space of neural networks. Users are allowed to flexibly select instance images, their clusters, and compare them regarding the specified visual representation of attributes. The exploration is guided by the manifestation of model performance related to mutual relationships among attributes, which often affect the learning accuracy and effectiveness. The system thus supports domain scientists to improve the training dataset and model, find questionable attributes labels, and identify outlier images or spurious data clusters. Case studies and scientists feedback demonstrate its functionalities and usefulness.

We propose a method for early recognition of human actions, one that can take advantages of multiple cameras while satisfying the constraints due to limited communication bandwidth and processing power. Our method considers multiple cameras, and at each time step, it will decide the best camera to use so that a confident recognition decision can be reached as soon as possible. We formulate the camera selection problem as a sequential decision process, and learn a view selection policy based on reinforcement learning. We also develop a novel recurrent neural network architecture to account for the unobserved video frames and the irregular intervals between the observed frames. Experiments on three datasets demonstrate the effectiveness of our approach for early recognition of human actions.

In crowd counting, each training image contains multiple people, where each person is annotated by a dot. Existing crowd counting methods need to use a Gaussian to smooth each annotated dot or to estimate the likelihood of every pixel given the annotated point. In this paper, we show that imposing Gaussians to annotations hurts generalization performance. Instead, we propose to use Distribution Matching for crowd COUNTing (DM-Count). In DM-Count, we use Optimal Transport (OT) to measure the similarity between the normalized predicted density map and the normalized ground truth density map. To stabilize OT computation, we include a Total Variation loss in our model. We show that the generalization error bound of DM-Count is tighter than that of the Gaussian smoothed methods. In terms of Mean Absolute Error, DM-Count outperforms the previous state-of-the-art methods by a large margin on two large-scale counting datasets, UCF-QNRF and NWPU, and achieves the state-of-the-art results on the ShanghaiTech and UCF-CC50 datasets. DM-Count reduced the error of the state-of-the-art published result by approximately 16%. Code is available at https://github.com/cvlab-stonybrook/DM-Count.

In this paper, we propose a novel visual information based framework to solve the real-time speech activity detection problem. Unlike conventional methods which commonly use the audio signal as input, our approach incorporates facial information into a deep neural network for feature learning. Instead of using the whole input image, we further develop a novel end-to-end landmark pooling network to act as an attention-guide scheme to help the deep neural network only focus the related portion of the input image. This helps the network to precisely and efficiently learn highly discriminative features for speech activities. What's more, we implement a recurrent neural network with the gated recurrent unit scheme to make use of the sequential information from video to produce the final decision. To give a comprehensive evaluation of the proposed method, we collect a large-scale dataset from unconstrained speech activities, which consists of a large number of speech/non-speech video sequences under various kinds of degradation. Experimental results demonstrate the superiority of our proposed pipeline over previous approach in terms of performance and efficiency.

Human action recognition and body movement prediction are important tasks. They are different and have traditionally been addressed separately. These tasks, however, provide mutual benefits to each other, and existing methods fail to capture these benefits. In this paper, we propose a method for jointly recognizing the action and predicting the movement of a person. Our method is based on two Long-Short Term Memory (LSTM) recurrent neural networks, but extend them to provide and receive benefits of each other. In particular, we design two LSTM architectures. One LSTM can generate a sequence of body movement conditioned on the past movement and the predicted class of the action, and the other LSTM can recognize the human action based on the predicted sequence of body movement. Experiments on Montalbano and MSR Action 3D datasets show that movement prediction provides benefits to early recognition of human action, which in turn improves the quality of the predicted movement.

Detecting segments of interest from an input sequence is a challenging problem which often requires not only good knowledge of individual target segments, but also contextual understanding of the entire input sequence and the relationships between the target segments. To address this problem, we propose the Sequence-to-Segment Network (S$^2$N), a novel end-to-end sequential encoder-decoder architecture. S$^2$N first encodes the input into a sequence of hidden states that progressively capture both local and holistic information. It then employs a novel decoding architecture, called Segment Detection Unit (SDU), that integrates the decoder state and encoder hidden states to detect segments sequentially. During training, we formulate the assignment of predicted segments to ground truth as bipartite matching and use the Earth Mover's Distance to calculate the localization errors. We experiment with S$^2$N on temporal action proposal generation and video summarization and show that S$^2$N achieves state-of-the-art performance on both tasks.

Visual inspection of x-ray scattering images is a powerful technique for probing the physical structure of materials at the molecular scale. In this paper, we explore the use of deep learning to develop methods for automatically analyzing x-ray scattering images. In particular, we apply Convolutional Neural Networks and Convolutional Autoencoders for x-ray scattering image classification. To acquire enough training data for deep learning, we use simulation software to generate synthetic x-ray scattering images. Experiments show that deep learning methods outperform previously published methods by 10% on synthetic and real datasets.