93 accepted papers
Accurate simulation of terrestrial ecological carbon cycles is crucial for global climate change and ecosystem management. Process-based carbon models have high interpretability, but suffer from insufficient accuracy and slow computation due to fixed parameters. In contrast, deep-learning carbon mod
Open-vocabulary change detection (OVCD) seeks to recognize arbitrary changes of interest by enabling generalization beyond a fixed set of predefined classes. We reformulate OVCD as a two-stage pipeline: first generate class-agnostic change proposals using visual foundation models (VFMs) such as SAM
Current diffusion-based portrait animation models predominantly focus on enhancing visual quality and expression realism, while overlooking generation latency and real-time performance, which restricts their application range in the live streaming scenario. We propose PersonaLive, a novel diffusion-
With the rapid expansion of photovoltaic (PV) power generation worldwide, PV systems have become key to global energy construction. Accurate PV forecasting is essential for safe grid operation and renewable energy integration. However, most existing models rely heavily on site-specific historical da
Rip currents cause over 100 drowning deaths and more than 30,000 rescues annually in the United States, posing a severe threat to beach safety worldwide. However, most existing detection methods are reactive, identifying rip currents only after they form, leaving limited time for intervention. We pr
The growing adoption of XR devices has fueled strong demand for high-quality stereo video, yet its production remains costly and artifact-prone.To address this challenge, we present **StereoWorld**, an **end-to-end framework** that repurposes a pretrained video generator for high-fidelity monocular-
We investigate the challenge of applying Large Language Models (LLMs) to long texts. We propose a theoretical framework that distinguishes the failure modes of long context tasks into three categories: cross-chunk dependence (task noise), confusion that grows with context size (model noise), and the…
With the widespread adoption of Mixture-of-Experts (MoE) models, there is a growing demand for efficient inference on memory-constrained devices. While offloading expert parameters to CPU memory and loading activated experts on demand has emerged as a potential solution, the large size of activated…
Is there a foreign language describing protein sequences and structures simultaneously? Protein structures, represented by continuous 3D points, have long posed a challenge due to the contrasting modeling paradigms of discrete sequences. We introduce FoldTokenizer to represent protein sequence-struc…
Building helpful and harmless large language models (LLMs) requires effective model alignment approach based on human instructions and feedback, which necessitates high-quality human-labeled data. Constructing such datasets is often expensive and hard to scale, and may face potential limitations on…
Large language model inference is both memory-intensive and time-consuming, often requiring distributed algorithms to efficiently scale. Various model parallelism strategies are used in multi-gpu training and inference to partition computation across multiple devices, reducing memory load and comput…
Over 4.15 million low-income households across nearly 60,000 villages in China benefit from photovoltaic (PV) poverty alleviation power stations. However, weak infrastructure and limited capabilities make these systems vulnerable to fluctuations. One of the United Nations' Sustainable Development Go
Recent advances in large language models (LLMs) demonstrate substantial capabilities in natural language understanding and generation tasks. With the growing number of LLMs, how to harness the collective expertise of multiple LLMs is an exciting open direction. Toward this goal, we propose a new app…
Multivariate time series (MTS) forecasting presents significant challenges due to the diverse noise distributions and complex periodic patterns across different channels. Existing Transformer-based models often apply uniform noise reduction techniques and simplistic patch segmentation, resulting in…
Deep-learning-based lossless compression is of immense importance in real-world applications, such as cold data persistence, sensor data collection, and astronomical data transmission. However, existing compressors typically model data using single-byte symbols as tokens, which makes it hard to capt
Large Language Models (LLMs) struggle with long-context reasoning, not only due to the quadratic scaling of computational complexity with sequence length but also because of the scarcity and expense of annotating long-context data. There has been barely any open-source work that systematically ablat…
Large Language Models (LLMs) have significantly advanced natural language processing with exceptional task generalization capabilities. Low-Rank Adaption (LoRA) offers a cost-effective fine-tuning solution, freezing the original model parameters and training only lightweight, low-rank adapter matric…
In this work, we present Patch-Adapter, an effective framework for high-resolution text-guided image inpainting. Unlike existing methods limited to lower resolutions, our approach achieves 4K+ resolution while maintaining precise content consistency and prompt alignment--two critical challenges in i…
We present a novel inference scheme, self-speculative decoding, for accelerating Large Language Models (LLMs) without the need for an auxiliary model. This approach is characterized by a two-stage process: drafting and verification. The drafting stage generates draft tokens at a slightly lower quali…
Model compression is one of the most popular approaches to improve the accessibility of Large Language Models (LLMs) by reducing their memory footprint. However, the gaining of such efficiency benefits often simultaneously demands extensive engineering efforts and intricate designs to mitigate the p…
"Recent video masked autoencoder (MAE) works have designed improved masking algorithms focused on saliency. These works leverage visual cues such as motion to mask the most salient regions. However, the robustness of such visual cues depends on how often input videos match underlying assumptions. On…
Molecule inverse folding has been a long-standing challenge in chemistry and biology, with the potential to revolutionize drug discovery and material science. Despite specified models have been proposed for different small- or macro-molecules, few have attempted to unify the learning process, result…
As the scale of data and models for video understanding rapidly expand, handling long-form video input in transformer-based models presents a practical challenge. Rather than resorting to input sampling or token dropping, which may result in information loss, token merging shows promising results wh…
Reconstructing two hands from monocular RGB images is challenging due to frequent occlusion and mutual confusion. Existing methods mainly learn an entangled representation to encode two interacting hands, which are incredibly fragile to impaired interaction, such as truncated hands, separate hands,…
Distributed training of foundation models, especially large language models (LLMs), is communication-intensive and so has heavily relied on centralized data centers with fast interconnects. Can we train on slow networks and unlock the potential of decentralized infrastructure for foundation models?…
Speech-driven 3D facial animation has been widely studied, yet there is still a gap to achieving realism and vividness due to the highly ill-posed nature and scarcity of audio-visual data. Existing works typically formulate the cross-modal mapping into a regression task, which suffers from the regre…
Image inpainting aims to fill the missing hole of the input. It is hard to solve this task efficiently when facing high-resolution images due to two reasons: (1) Large reception field needs to be handled for high-resolution image inpainting. (2) The general encoder and decoder network synthesizes ma…
Large language models (LLMs) with hundreds of billions of parameters have sparked a new wave of exciting AI applications. However, they are computationally expensive at inference time. Sparsity is a natural approach to reduce this cost, but existing methods either require costly retraining, have to…
Continual learning is known for suffering from catastrophic forgetting, a phenomenon where previously learned concepts are forgotten upon learning new tasks. A natural remedy is to use trained models for old tasks as ‘teachers’ to regularize the update of the current model to prevent such forgetting…
We present a novel paradigm for high-fidelity face swapping that faithfully preserves the desired subtle geometry and texture details. We rethink face swapping from the perspective of fine-grained face editing, i.e., editing for swapping (E4S), and propose a framework that is based on the explicit d…
Long-term time series forecasting (LTSF) provides substantial benefits for numerous real-world applications, whereas places essential demands on the model capacity to capture long-range dependencies. Recent Transformer-based models have significantly improved LTSF performance. It is worth noting tha…
This paper proposes an anchor-based deformation model, namely AnchorDEF, to predict 3D garment animation from a body motion sequence. It deforms a garment mesh template by a mixture of rigid transformations with extra nonlinear displacements. A set of anchors around the mesh surface is introduced to…
Several recent works have directly extended the image masked autoencoder (MAE) with random masking into video domain, achieving promising results. However, unlike images, both spatial and temporal information are important for video understanding. This suggests that the random masking strategy that…
We target a 3D generative model for general natural scenes that are typically unique and intricate. Lacking the necessary volumes of training data, along with the difficulties of having ad hoc designs in presence of varying scene characteristics, renders existing setups intractable. Inspired by clas…
Effective modeling of complex spatiotemporal dependencies in long-form videos remains an open problem. The recently proposed Structured State-Space Sequence (S4) model with its linear complexity offers a promising direction in this space. However, we demonstrate that treating all image-tokens equall…
The quality of training data impacts the performance of pre-trained large language models (LMs). Given a fixed budget of tokens, we study how to best select data that leads to good downstream model performance across tasks. We develop a new framework based on a simple hypothesis: just as humans acqu…
A good motion retargeting cannot be reached without reasonable consideration of source-target differences on both the skeleton and shape geometry levels. In this work, we propose a novel Residual RETargeting network (R2ET) structure, which relies on two neural modification modules, to adjust the sou…
Learning with noisy label is a classic problem that has been extensively studied for image tasks, but much less for video in the literature. A straightforward migration from images to videos without considering temporal semantics and computational cost is not a sound choice. In this paper, we propos…
Neural volume rendering enables photo-realistic renderings of a human performer in free-view, a critical task in immersive VR/AR applications. But the practice is severely limited by high computational costs in the rendering process. To solve this problem, we propose the UV Volumes, a new approach t…
Pretraining Vision Transformers (ViTs) has achieved great success in visual recognition. A following scenario is to adapt a ViT to various image and video recognition tasks. The adaptation is challenging because of heavy computation and memory storage. Each model needs an independent and complete fi…
Deep neural networks (DNNs) have been shown to be vulnerable to adversarial examples, which can produce erroneous predictions by injecting imperceptible perturbations. In this work, we study the transferability of adversarial examples, which is significant due to its threat to real-world application…
Federated learning (FL) is a promising approach for learning a shared global model on decentralized data owned by multiple clients without exposing their privacy. In real-world scenarios, data accumulated at the client-side varies in distribution over time. As a consequence, the global model tends t…
Neural Radiance Field (NeRF) has gained considerable attention recently for 3D scene reconstruction and novel view synthesis due to its remarkable synthesis quality. However, image blurriness caused by defocus or motion, which often occurs when capturing scenes in the wild, significantly degrades it…
Video transformers have recently emerged as an effective alternative to convolutional networks for action classification. However, most prior video transformers adopt either global space-time attention or hand-defined strategies to compare patches within and across frames. These fixed attention sche…
Programmable surfaces (PSs) consist of a 2D array of actuators that can deform in the third dimension, providing the ability to create continuous 3D profiles. Discrete PSs can be realized using an array of independent solid linear actuators. Continuous PSs consist of actuators that are mechanically
Vision Transformers (ViTs) take all the image patches as tokens and construct multi-head self-attention (MHSA) among them. Complete leverage of these image tokens brings redundant computations since not all the tokens are attentive in MHSA. Examples include that tokens containing semantically meanin…
Weakly-supervised temporal action localization aims to localize actions in untrimmed videos with only video-level labels. Most existing methods address this problem with a "localization-by-classification" pipeline that localizes action regions based on snippet-wise classification sequences. Snippet-…
Previous portrait image generation methods roughly fall into two categories: 2D GANs and 3D-aware GANs. 2D GANs can generate high fidelity portraits but with low view consistency. 3D-aware GAN methods can maintain view consistency but their generated images are not locally editable. To overcome thes…
Communication compression is a crucial technique for modern distributed learning systems to alleviate their communication bottlenecks over slower networks. Despite recent intensive studies of gradient compression for data parallel-style training, compressing the activations for models trained with p…
Neural Radiance Fields (NeRF) has recently gained popularity for its impressive novel view synthesis ability. This paper studies the problem of hallucinated NeRF: i.e., recovering a realistic NeRF at a different time of day from a group of tourism images. Existing solutions adopt NeRF with a control…
We present a novel high-fidelity generative adversarial network (GAN) inversion framework that enables attribute editing with image-specific details well-preserved (e.g., background, appearance, and illumination). We first analyze the challenges of high-fidelity GAN inversion from the perspective of…
Adversarial training (AT) is always formulated as a minimax problem, of which the performance depends on the inner optimization that involves the generation of adversarial examples (AEs). Most previous methods adopt Projected Gradient Decent (PGD) with manually specifying attack parameters for AE ge…
"Video-Text Pre-training (VTP) aims to learn transferable representations for various downstream tasks from large-scale web videos. To date, almost all existing VTP methods are limited to retrieval-based downstream tasks, e.g., video retrieval, whereas their transfer potentials on localization-based…
Video transformers have recently emerged as a competitive alternative to 3D CNNs for video understanding. However, due to their large number of parameters and reduced inductive biases, these models require supervised pretraining on large-scale image datasets to achieve top performance. In this paper…
In light of the success of contrastive learning in the image domain, current self-supervised video representation learning methods usually employ contrastive loss to facilitate video representation learning. When naively pulling two augmented views of a video closer, the model however tends to learn…
We study the problem of multi-robot active mapping, which aims for complete scene map construction in minimum time steps. The key to this problem lies in the goal position estimation to enable more efficient robot movements. Previous approaches either choose the frontier as the goal position via a m…
State-of-the-art deepfake detectors perform well in identifying forgeries when they are evaluated on a test set similar to the training set, but struggle to maintain good performance when the test forgeries exhibit different characteristics from the training images e.g., forgeries are created by uns…
Free-form text prompts allow users to describe their intentions during image manipulation conveniently. Based on the visual latent space of StyleGAN[21] and text embedding space of CLIP[34], studies focus on how to map these two latent spaces for text-driven attribute manipulations. Currently, the l…
"Fast adversarial training (FAT) effectively improves the efficiency of standard adversarial training (SAT). However, initial FAT encounters catastrophic overfitting, i.e., the robust accuracy against adversarial attacks suddenly decreases to 0% during training. Though several FAT variants spare no…
Recent studies in deepfake detection have yielded promising results when the training and testing face forgeries are from the same dataset. However, the problem remains challenging when one tries to generalize the detector to forgeries created by unseen methods in the training dataset. This work add…
In this paper, we propose SkipBERT to accelerate BERT inference by skipping the computation of shallow layers. To achieve this, our approach encodes small text chunks into independent representations, which are then materialized to approximate the shallow representation of BERT. Since the use of suc…
"Image harmonization aims to modify the color of the composited region according to the specific background. Previous works model this task as a pixel-wise image translation using UNet family structures. However, the model size and computational cost limit the ability of their models on edge devices…
In adversarial machine learning, deep neural networks can fit the adversarial examples on the training dataset but have poor generalization ability on the test set. This phenomenon is called robust overfitting, and it can be observed when adversarially training neural nets on common datasets, includ…
"One-shot talking face generation aims at synthesizing a high-quality talking face video from an arbitrary portrait image, driven by a video or an audio segment. In this work, we provide a solution from a novel perspective that differs from existing frameworks. We first investigate the latent featur…
"In this work, we tackle the problem of active camera localization, which controls the camera movements actively to achieve an accurate camera pose. The past solutions are mostly based on Markov Localization, which reduces the position-wise camera uncertainty for localization. These approaches local…
Unsupervised video representation learning has made remarkable achievements in recent years. However, most existing methods are designed and optimized for video classification. These pre-trained models can be sub-optimal for temporal localization tasks due to the inherent discrepancy between video-l…
Pre-training video transformers on extra large-scale datasets is generally required to achieve premier performance on relatively small datasets. In this paper, we show that video masked autoencoders (VideoMAE) are data-efficient learners for self-supervised video pre-training (SSVP). We are inspired…
Slot filling is a challenging task in Spoken Language Understanding (SLU). Supervised methods usually require large amounts of annotation to maintain desirable performance. A solution to relieve the heavy dependency on labeled data is to employ bootstrapping, which leverages unlabeled data. However,…
Recent research has been remarkable in recurrent neural networks (RNNs) on sequence-to-sequence problems for image caption, and promising in convolutional neural networks (CNNs) on spatial analysis problems for image detection and sematic segmentation problems. In this paper, based on recurrent neur…
Studies on self-supervised visual representation learning (SSL) improve encoder backbones to discriminate training samples without labels. While CNN encoders via SSL achieve comparable recognition performance to those via supervised learning, their network attention is under-explored for further imp…
We present an unsupervised learning approach for optical flow estimation by improving the upsampling and learning of pyramid network. We design a self-guided upsample module to tackle the interpolation blur problem caused by bilinear upsampling between pyramid levels. Moreover, we propose a pyramid…
We present Vx2Text, a framework for text generation from multimodal inputs consisting of video plus text, speech, or audio. In order to leverage transformer networks, which have been shown to be effective at modeling language, each modality is first converted into a set of language embeddings by a l…
Homography estimation is a basic image alignment method in many applications. It is usually done by extracting and matching sparse feature points, which are error-prone in low-light and low-texture images. On the other hand, previous deep homography approaches use either synthetic images for supervi…
Generating accurate descriptions for online fashion items is important not only for enhancing customers' shopping experiences, but also for the increase of online sales. Besides the need of correctly presenting the attributes of items, the expressions in an enchanting style could better attract cust…
Deep learning-based image denoising approaches have been extensively studied in recent years, prevailing in many public benchmark datasets. However, the stat-of-the-art networks are computationally too expensive to be directly applied on mobile devices. In this work, we propose a light-weight, effic…
We introduce the task of scene-aware dialog. Our goal is to generate a complete and natural response to a question about a scene, given video and audio of the scene and the history of previous turns in the dialog. To answer successfully, agents must ground concepts from the question in the video whi…
Most previous image matting methods require a roughly-specificed trimap as input, and estimate fractional alpha values for all pixels that are in the unknown region of the trimap. In this paper, we argue that directly estimating the alpha matte from a coarse trimap is a major limitation of previous…
In order for machines interacting with the real world to have conversations with users about the objects and events around them, they need to understand dynamic audiovisual scenes. The recent revolution of neural network models allows us to combine various modules into a single end-to-end differenti…
Graphics Interchange Format (GIF) is a highly portable graphics format that is ubiquitous on the Internet. Despite their small sizes, GIF images often contain undesirable visual artifacts such as flat color regions, false contours, color shift, and dotted patterns. In this paper, we propose GIF2Vide…
One-class learning is the classic problem of fitting a model to data for which annotations are available only for a single class. In this paper, we propose a novel objective for one-class learning. Our key idea is to use a pair of orthonormal frames -- as subspaces -- to "sandwich" the labeled data…
Surface-based geodesic topology provides strong cues for object semantic analysis and geometric modeling. However, such connectivity information is lost in point clouds. Thus we introduce GeoNet, the first deep learning architecture trained to model the intrinsic structure of surfaces represented as…
Not all the human body parts have the same degree of freedom (DOF) due to the physiological structure. For example, the limbs may move more flexibly and freely than the torso does. Most of the existing 3D pose estimation methods, despite the very promising results achieved, treat the body joints equ…
We present a new data-driven method for robust skin detection from a single human portrait image. Unlike previous methods, we incorporate human body as a weak semantic guidance into this task, considering acquiring large-scale of human labeled skin data is commonly expensive and time-consuming. To b…
Capturing document images is a common way for digitizing and recording physical documents due to the ubiquitousness of mobile cameras. To make text recognition easier, it is often desirable to digitally flatten a document image when the physical document sheet is folded or curved. In this paper, we…
Adversarial perturbations are noise-like patterns that can subtly change the data, while failing an otherwise accurate classifier. In this paper, we propose to use such perturbations for improving the robustness of video representations. To this end, given a well-trained deep model for per-frame vid…
In single image deblurring, the ``coarse-to-fine'' scheme, i.e. gradually restoring the sharp image on different resolutions in a pyramid, is very successful in both traditional optimization-based methods and recent neural-network-based approaches. In this paper, we investigate this strategy and pro…
Popular deep models for action recognition in videos generate independent predictions for short clips, which are then pooled heuristically to assign an action label to the full video segment. As not all frames may characterize the underlying action---indeed, many are common across multiple actions--…
Motion blur from camera shake is a major problem in videos captured by hand-held devices. Unlike single-image deblurring, video-based approaches can take advantage of the abundant information that exists across neighboring frames. As a result the best performing methods rely on the alignment of near…
Previous CNN-based video super-resolution approaches need to align multiple frames to the reference. In this paper, we show that proper frame alignment and motion compensation is crucial for achieving high quality results. We accordingly propose a 'sub-pixel motion compensation' (SPMC) layer in a CN…
In this paper, we study an unconventional but practically meaningful reversibility problem of commonly used image filters. We broadly define filters as operations to smooth images or to produce layers via global or local algorithms. And we raise the intriguingly problem if they are reservable to the…
We present a fully automatic approach to detect and segment fence-like occluders from a video clip. Unlike previous approaches that usually assume either static scenes or cameras, our method is capable of handling both dynamic scenes and moving cameras. Under a bottom-up framework, it first clusters…
Interactive video segmentation systems aim at producing sub-pixel-level object boundaries for visual effect applications. Recent approaches mainly focus on using sparse user input (i.e. scribbles) for efficient segmentation; however, the quality of the final object boundaries is not satisfactory for…
Optical aberration widely exists in optical imaging systems, especially in consumer-level cameras. In contrast to previous solutions using hardware compensation or pre-calibration, we propose a computational approach for blind aberration removal from a single image, by exploring various geometric an…