106 accepted papers
While Multimodal Large Language Models (MLLMs) have achieved remarkable progress in general visual understanding, they suffer from a fundamental geometric fragility: standard visual representations often degrade rapidly under changes in viewpoint and viewing distance. Our analysis identifies that ex…
While 3D Gaussian Splatting (3DGS) has demonstrated impressive real-time rendering performance, its efficacy remains constrained by a reliance on heuristic density control. Despite numerous refinements to these handcrafted rules, such methods inherently lack the flexibility to adapt to diverse scene…
High-resolution (HR) image perception presents a key bottleneck for multimodal large language models (MLLMs). While visual search offers a promising solution, existing methods struggle with the trade-off between coverage and efficiency. Visual expert-assisted search is efficient but prone to blind s…
Large-scale video-language pretraining enables strong generalization across multimodal tasks but often incurs prohibitive computational costs. Although recent advances in masked visual modeling help mitigate this issue, they still suffer from two fundamental limitations: severe visual information lo
Existing works on reasoning segmentation either connect hidden features from a language model directly to a mask decoder or represent positions in text, which limits interpretability and semantic detail. To solve this, we present CoPRS, a Multi-modal Chain-of-Thought (MCoT)–based positional percepti…
Composed Video Retrieval aims to retrieve a target video given a reference video and a textual modification describing the desired change. The core challenge lies in modeling compositional multimodal transformations, i.e., how entities, actions, and scenes evolve across video and language modalities
Continual Test-Time Adaptation (CTTA) aims to empower perception systems to handle dynamic distribution shifts encountered after deployment. Existing methods predominantly follow a backward-alignment paradigm, which rigidly aligns incoming data with supervisory surrogates derived from the source dom
Model merging offers a promising paradigm for consolidating multiple expert models into a single multitask architecture. However, its effectiveness is often hindered by task interference, where conflicting parameter updates from different tasks degrade performance. While dynamic, Mixture-of-Experts
AI personal assistants, deployed through robots or wearables, require embodied understanding to collaborate effectively with humans. However, current Multimodal Large Language Models (MLLMs) primarily focus on third-person (exocentric) vision, overlooking the unique challenges of first-person (egoce
With the increasing exploration and exploitation of the underwater world, underwater images have become a critical medium for human interaction with marine environments, driving extensive research into their efficient transmission and storage. However, contemporary underwater image compression algor…
Partially Relevant Video Retrieval (PRVR) aims to retrieve untrimmed videos based on text queries that describe only partial events. Existing methods suffer from incomplete global contextual perception, struggling with query ambiguity and local noise induced by spurious responses. To address these i
Existing visual trackers mainly operate in a non-interactive, fire-and-forget manner, making them impractical for real-world scenarios that require human-in-the-loop adaptation. To overcome this limitation, we introduce Interactive Tracking, a new paradigm that allows users to guide the tracker at a
Weakly-supervised Video Anomaly Detection (wVAD) aims to detect abnormal events using only binary labels, making it challenging to capture both the diversity of anomalies and their shared semantic cues. Existing methods either focus on a generic anomaly pattern, achieving strong generalization but w
Linear attention mitigates the quadratic complexity of softmax attention but suffers from a critical loss of expressiveness. We identify two primary causes: (1) The normalization operation cancels the query norm, which breaks the correlation between a query's norm and the spikiness (entropy) of the …
Dataset distillation aims to generate compact synthetic datasets that enable models trained on them to achieve performance comparable to those trained on full real datasets, while substantially reducing storage and computational costs. Early bi-level optimization methods (e.g., MTT) have shown promi…
Partially relevant video retrieval aims to retrieve untrimmed videos using text queries that describe only partial content. However, the inherent asymmetry between brief queries and rich video content inevitably introduces uncertainty into the retrieval process. In this setting, vague queries often …
While large language models provide strong compositional reasoning, existing reasoning segmentation pipelines fail to transparently connect this reasoning to visual perception. Current methods, such as latent query alignment, are end-to-end yet opaque "black boxes". Conversely, textual localization
Vision-Language Models (VLMs) inherit the auto-regressive generation paradigm and cache the keys and values (KV) of all previous tokens to accelerate inference, resulting in memory consumption that scales linearly with context length. This issue is particularly pronounced in VLMs due to substantial …
Multimodal Large Language Models (MLLMs) have achieved impressive progress in vision–language alignment, yet they remain limited in visual–spatial reasoning. We first identify that this limitation arises from the attention mechanism: visual tokens are overshadowed by language tokens, preventing the…
Large language models (LLMs) are increasingly being adopted to develop general-purpose AI agents. However, it remains challenging for these LLM-based AI agents to efficiently learn from feedback and iteratively optimize their strategies. To address this challenge, tremendous efforts have been dedica
Conditional image generation has gained significant attention for its ability to personalize content. However, the field faces challenges in developing task-agnostic, reliable, and explainable evaluation metrics. This paper introduces CIGEval, a unified agentic framework for comprehensive evaluation…
3D Gaussian Splatting (3DGS) has witnessed its rapid development in novel view synthesis, which attains high quality reconstruction and real-time rendering. At the same time, there is still a gap before implicit neural representation (INR) can become a practical compressor due to the lack of stream…
Self-Supervised Video Hashing (SSVH) compresses videos into hash codes for efficient indexing and retrieval using unlabeled training videos. Existing approaches rely on random frame sampling to learn video features and treat all frames equally. This results in suboptimal hash codes, as it ignores fr…
Visual representation models leveraging attention mechanisms are challenged by significant computational overhead, particularly when pursuing large receptive fields. In this study, we aim to mitigate this challenge by introducing the Heat Conduction Operator (HCO) built upon the physical heat conduc…
Zero-shot anomaly detection (ZSAD) is dedicated to detecting anomalies without having any seen normal or abnormal samples for the target set. Existing approaches utilize the pre-trained CLIP to assess normality/abnormality by exploiting the similarity between images and text with the frozen visual e…
Learned image compression (LIC) demonstrates superior rate-distortion (RD) performance compared to traditional methods. Recent method MambaVC attempts to introduce Mamba, a variant of state space models, into this field aim to establish a new paradigm beyond convolutional neural networks and transfo…
In practice, environments constantly change over time and space, posing significant challenges for object detectors trained based on a closed-set assumption, i.e., training and test data share the same distribution. To this end, continual test-time adaptation has attracted much attention, aiming to…
Transformer-based Large Language Models (LLMs) have exhibited remarkable success in extensive tasks primarily attributed to self-attention mechanism, which requires a token to consider all preceding tokens as its context to compute attention. However, when the context length L becomes very large (e.…
3D Question Answering (3D QA) requires the model to comprehensively understand its situated 3D scene described by the text, then reason about its surrounding environment and answer a question under that situation. However, existing methods usually rely on global scene perception from pure 3D point c…
Reconstructing high-quality images under low bitrates conditions presents a challenge, and previous methods have made this task feasible by leveraging the priors of diffusion models. However, the effective exploration of pre-trained latent diffusion models and semantic information integration in im…
Mamba-based architectures have shown to be a promising new direction for deep learning models owing to their competitive performance and sub-quadratic deployment speed. However, current Mamba multi-modal large language models (MLLM) are insufficient in extracting visual features, leading to imbalanc…
Reinforcement Learning (RL) algorithms for safety alignment of Large Language Models (LLMs), such as Direct Preference Optimization (DPO), encounter the challenge of distribution shift. Current approaches typically address this issue through online sampling from the target policy, which requires sig…
Visual In-Context Learning (VICL) enables adaptively solving vision tasks by leveraging pixel demonstrations, mimicking human-like task completion through analogy. Prompt selection is critical in VICL, but current methods assume the existence of a single "ideal" prompt in a pool of candidates, which…
Partially Relevant Video Retrieval (PRVR) addresses the critical challenge of matching untrimmed videos with text queries describing only partial content. Existing methods suffer from geometric distortion in Euclidean space that sometimes misrepresents the intrinsic hierarchical structure of videos…
Recent Large Vision Language Models (LVLMs) demonstrate promising capabilities in unifying visual understanding and generative modeling, enabling both accurate content understanding and flexible editing. However, current approaches treat \textbf{\textit{"what to see"}} and \textbf{\textit{"how to ed…
Centerline graphs, crucial for path planning in autonomous driving, are traditionally learned using deterministic methods. However, these methods often lack spatial reasoning and struggle with occluded or invisible centerlines. Generative approaches, despite their potential, remain underexplored in…
Asymmetric retrieval is a typical scenario in real-world retrieval systems, where compatible models of varying capacities are deployed on platforms with different resource configurations. Existing methods generally train pre-defined networks or subnetworks with capacities specifically designed for p…
With the explosive growth of video data, finding videos that meet detailed requirements in large datasets has become a challenge. To address this, the composed video retrieval task has been introduced, enabling users to retrieve videos using complex queries that involve both visual and textual infor…
Tracking and segmenting multiple similar objects with distinct or complex parts in long-term videos is particularly challenging due to the ambiguity in identifying target components and the confusion caused by occlusion, background clutter, and changes in appearance or environment over time. In this…
Transformer-based algorithms, such as LoRAT, have significantly enhanced object-tracking performance. However, these approaches rely on a standard attention mechanism, which incurs quadratic token complexity, making real-time inference computationally expensive. In this paper, we introduce LoRATv2,…
Composed Image Retrieval (CIR) enables users to search for images using multimodal queries that combine text and reference images. While metric learning methods have shown promise, they rely on deterministic point embeddings that fail to capture the inherent uncertainty in the input data, in which u…
The growing use of deep learning necessitates efficient network design and deployment, making neural predictors vital for estimating attributes such as accuracy and latency. Recently, Graph Neural Networks (GNNs) and transformers have shown promising performance in representing neural architectures.…
Large Language Models (LLMs) suffer severe performance degradation when facing extremely low-bit (sub 2-bit) quantization. Several existing sub 2-bit post-training quantization (PTQ) methods utilize a mix-precision scheme by leveraging an unstructured fine-grained mask to explicitly distinguish sali…
Most current precipitation nowcasting methods aim to capture the underlying spatiotemporal dynamics of precipitation systems by minimizing the mean square error (MSE). However, these methods often neglect effective constraints on the data distribution, leading to unsatisfactory prediction accuracy a…
In this paper, we explore a novel federated multimodal instruction tuning task(FedMIT), which is significant for collaboratively fine-tuning MLLMs on different types of multimodal instruction data on distributed devices. To solve the new task, we propose a federated multimodal instruction tuning fra…
Remote sensing foundation models largely break away from the traditional paradigm of designing task-specific models, offering greater scalability across multiple tasks. However, they face challenges such as low computational efficiency and limited interpretability, especially when dealing with large…
Automatic Depression Detection (ADD) garners widespread attention due to its convenience and objectivity. While existing research makes significant progress, challenges remain. First, most current ADD methods struggle to balance computational overhead and prediction accuracy. Second, these methods p…
Understanding human behavior and the environmental information in the egocentric video is very challenging due to the invisibility of some actions (e.g., laughing and sneezing) and the local nature of the first-person view. Leveraging the corresponding exocentric video to provide global context has…
Visual-spatial understanding, the ability to infer object relationships and layouts from visual input, is fundamental to downstream tasks such as robotic navigation and embodied interaction. However, existing methods face spatial uncertainty and data scarcity, limiting the 3D spatial reasoning capab…
Blind image super-resolution (blind SR) aims to restore a high-resolution (HR) image from a low-resolution (LR) image with unknown degradation. Many existing methods explicitly estimate degradation information from various LR images. However, in most cases, image degradations are independent of imag…
The development of self-supervised video-language models based on mask learning has significantly advanced downstream video tasks. These models leverage masked reconstruction to facilitate joint learning of visual and linguistic information. However, recent study reveals that reconstructing image fe…
Assessing the video comprehension capabilities of multimodal AI systems can effectively measure their understanding and reasoning abilities. Most video evaluation benchmarks are limited to a single language, typically English, and predominantly feature videos rooted in Western cultural contexts. In…
The misuse of large language models (LLMs), such as academic plagiarism, has driven the development of detectors to identify LLM-generated texts. To bypass these detectors, paraphrase attacks have emerged to purposely rewrite these texts to evade detection. Despite the success, existing methods requ
Text-based Person Retrieval (TPR) aims to retrieve the target person images given a textual query. The primary challenge lies in bridging the substantial gap between vision and language modalities, especially when dealing with limited large-scale datasets. In this paper, we introduce a CLIP-based Sy…
Over the past decade most methods in visual place recognition (VPR) have used neural networks to produce feature representations. These networks typically produce a global representation of a place image using only this image itself and neglect the cross-image variations (e.g. viewpoint and illumina…
Training neural networks with good generalization requires large computational costs in many deep learning methods due to large-scale datasets and over-parameterized models. Despite the emergence of a number of coreset selection methods to reduce the computational costs, the problem of coreset distr…
The main streams of human activity recognition (HAR) algorithms are developed based on RGB cameras which usually suffer from illumination, fast motion, privacy preservation, and large energy consumption. Meanwhile, the biologically inspired event cameras attracted great interest due to their unique…
Vector quantization (VQ) is a key technique in high-resolution and high-fidelity image synthesis, which aims to learn a codebook to encode an image with a sequence of discrete codes and then generate an image in an auto-regression manner. Although existing methods have shown superior performance,…
This paper presents M$^3$GPT, an advanced $\textbf{M}$ultimodal, $\textbf{M}$ultitask framework for $\textbf{M}$otion comprehension and generation. M$^3$GPT operates on three fundamental principles. The first focuses on creating a unified representation space for various motion-relevant modalities…
Popular transformer-based detectors detect objects in a one-to-one manner, where both the bounding box and category of each object are predicted only by the single query, leading to the box-sensitive category predictions. Additionally, the initialization of positional queries solely based on the pre…
Video-based Unsupervised Domain Adaptation (VUDA) method improves the generalization of the video model enabling it to be applied to action recognition tasks in different environments. However these methods require continuous access to source data during the adaptation process which are impractical…
The challenge of interpreting the world from a human perspective in Artificial Intelligence (AI) is particularly evident in egocentric video question answering, which grapples with issues like small object recognition, noise suppression, and spatial-temporal reasoning. To address these challenges, w…
Constrained by the separate encoding of vision and language, existing grounding and referring segmentation works heavily rely on bulky Transformer-based fusion en-/decoders and a variety of early-stage interaction technologies. Simultaneously, the current mask visual language modeling (MVLM) fails t…
Single-domain generalization aims to learn a model from single source domain data attaining generalized performance on other unseen target domains. Existing works primarily focus on improving the generalization ability of static networks. However static networks are unable to dynamically adapt to th…
Existing tracking methods mainly focus on learning better target representation or developing more robust prediction models to improve tracking performance. While tracking performance has significantly improved the target loss issue occurs frequently due to tracking failures complete occlusion or ou…
Crowd counting has achieved significant progress by training regressors to predict instance positions. In heavily crowded scenarios however regressors are challenged by uncontrollable annotation variance which causes density map bias and context information inaccuracy. In this study we propose mutua…
"Continual Test-Time Adaptation (CTTA) involves adapting a pre-trained source model to continually changing unsupervised target domains. In this paper, we systematically analyze the challenges of this task: online environment, unsupervised nature, and the risks of error accumulation and catastrophic…
"Story visualization aims to generate a series of realistic and coherent images based on a storyline. Current models adopt a frame-by-frame architecture by transforming the pre-trained text-to-image model into an auto-regressive manner. Although these models have shown notable progress, there are st…
The conventional deep learning paradigm often involves training a deep model on a server and then deploying the model or its distilled ones to resource-limited edge devices. Usually, the models shall remain fixed once deployed (at least for some period) due to the potential high cost of model adapta…
Recent studies show that vision models pre-trained in generic visual learning tasks with large-scale data can provide useful feature representations for a wide range of visual perception problems. However, few attempts have been made to exploit pre-trained foundation models in visual place recogniti…
Designing computationally efficient network architectures remains an ongoing necessity in computer vision. In this paper, we adapt Mamba, a state-space language model, into VMamba, a vision backbone with linear time complexity. At the core of VMamba is a stack of Visual State-Space (VSS) blocks with…
In this work, we study few-shot domain adaptive object detection (FSDAOD), where only a few target labeled images are available for training in addition to sufficient source labeled images. Critically, in FSDAOD, the data-scarcity in the target domain leads to an extreme data imbalance between the s…
Unsupervised domain adaptive object detection (UDA-OD) aims to learn a detector by generalizing knowledge from a labeled source domain to an unlabeled target domain. Though the existing graph-based methods for UDA-OD perform well in some cases, they cannot learn a proper node set for the graph. In a…
Existing visual tracking methods typically take an image patch as the reference of the target to perform tracking. However, a single image patch cannot provide a complete and precise concept of the target object as images are limited in their ability to abstract and can be ambiguous, which makes it…
Visual Question Answering (VQA) aims to answer a textual question based on a given image. Nevertheless, recent studies have shown that VQA models tend to capture the biases to answer the question, instead of using the reasoning ability, resulting in poor generalisation ability. To alleviate the issu…
In this paper, we present an integral pre-training framework based on masked image modeling (MIM). We advocate for pre-training the backbone and neck jointly so that the transfer gap between MIM and downstream recognition tasks is minimal. We make two technical contributions. First, we unify the rec…
This paper focuses on the prevalent stage interference and stage performance imbalance of incremental learning. To avoid obvious stage learning bottlenecks, we propose a new incremental learning framework, which leverages a series of stage-isolated classifiers to perform the learning task at each st…
Vision-and-language navigation (VLN) is the task to enable an embodied agent to navigate to a remote location following the natural language instruction in real scenes. Most of the previous approaches utilize the entire features or object-centric features to represent navigable candidates. However,…
Beyond achieving higher compression efficiency over classical image compression codecs, deep image compression is expected to be improved with additional side information, e.g., another image from a different perspective of the same scene. To better utilize the side information under the distributed…
Recently, pre-trained vision-language models have been increasingly used to tackle the challenging zero-shot segmentation task. Typical solutions follow the paradigm of first generating mask proposals and then adopting CLIP to classify them. To maintain the CLIP's zero-shot transferability, previous…
Domain gap between synthetic and real data in visual regression (e.g., 6D pose estimation) is bridged in this paper via global feature alignment and local refinement on the coarse classification of discretized anchor classes in target space, which imposes a piece-wise target manifold regularization…
Supervised visual captioning models typically require a large scale of images or videos paired with descriptions in a specific language (i.e., the vision-caption pairs) for training. However, collecting and labeling large-scale datasets is time-consuming and expensive for many scenarios and language…
Striking a balance between exploring the spatio-temporal correlation and controlling model complexity is vital for video-based crowd counting methods. In this paper, we propose a Recurrent Fine-Grained Self-Attention Network (RFSNet) to achieve efficient and accurate counting in video scenes via the…
We consider two biologically plausible structures, the Spiking Neural Network (SNN) and the self-attention mechanism. The former offers an energy-efficient and event-driven paradigm for deep learning, while the latter has the ability to capture feature dependencies, enabling Transformer to achieve g…
Token interaction operation is one of the core modules in MLP-based models to exchange and aggregate information between different spatial locations. However, the power of token interaction on the spatial dimension is highly dependent on the spatial resolution of the feature maps, which limits the m…
There is a growing interest in developing unlearnable examples (UEs) against visual privacy leaks on the Internet. UEs are training samples added with invisible but unlearnable noise, which have been found can prevent unauthorized training of machine learning models. UEs typically are generated via…
Active Learning (AL) aims to optimize basic learned model(s) iteratively by selecting and annotating unlabeled data samples that are deemed to best maximise the model performance with minimal required data. However, the learned model is easy to overfit due to the biased distribution (sampling bias a…
This paper focuses on crowd counting. As large-scale variations often exist within crowd images, neither fixed-size convolution kernel of CNN nor fixed-size attentions of recent vision transformers can well handle this kind of variations. To address this problem, we propose a Multifaceted Attention…
"Deep Metric Learning (DML) serves to learn an embedding function to project semantically similar data into nearby embedding space and plays a vital role in many applications, such as image retrieval and face recognition. However, the performance of DML methods often highly depends on sampling metho…
Semantic patterns of fine-grained objects are determined by subtle appearance difference of local parts, which thus inspires a number of part-based methods. However, due to uncontrollable object poses in images, distinctive details carried by local regions can be spatially distributed or even self-o…
In this paper, we study the problem of networked multi-agent reinforcement learning (MARL), where a number of agents are deployed as a partially connected network and each interacts only with nearby agents. Networked MARL requires all agents to make decisions in a decentralized manner to optimize a…
Despite the potential of multi-modal pre-training to learn highly discriminative feature representations from complementary data modalities, current progress is being slowed by the lack of large-scale modality-diverse datasets. By leveraging the natural suitability of E-commerce, where different mod…
"The exponentially large discrete search space in mixed-precision quantization (MPQ) makes it hard to determine the optimal bit-width for each layer. Previous works usually resort to iterative search methods on the training set, which consume hundreds or even thousands of GPU-hours. In this study, w…
We propose an end-to-end image compression and analysis model with Transformers, targeting to the cloud-based image classification application. Instead of placing an existing Transformer-based image classification model directly after an image codec, we aim to redesign the Vision Transformer (ViT) m…
Within Convolutional Neural Network (CNN), the convolution operations are good at extracting local features but experience difficulty to capture global representations. Within visual transformer, the cascaded self-attention modules can capture long-distance feature dependencies but unfortunately det…
One of the key steps in Neural Architecture Search (NAS) is to estimate the performance of candidate architectures. Existing methods either directly use the validation performance or learn a predictor to estimate the performance. However, these methods can be either computationally expensive or very…
Traditional crowd counting approaches usually use Gaussian assumption to generate pseudo density ground truth, which suffers from problems like inaccurate estimation of the Gaussian kernel sizes. In this paper, we propose a new measure-based counting approach to regress the predicted density maps to…
Deep reinforcement learning (RL) has been applied to traffic signal control recently and demonstrated superior performance to conventional control methods. However, there are still several challenges we have to address before fully applying deep RL to traffic signal control. Firstly, the objective o…
We propose a novel joint lossy image and residual compression framework for learning l_infinity-constrained near-lossless image compression. Specifically, we obtain a lossy reconstruction of the raw image through lossy image compression and uniformly quantize the corresponding residual to satisfy a…
Tracking by natural language specification is a new rising research topic that aims at locating the target object in the video sequence based on its language description. Compared with traditional bounding box (BBox) based tracking, this setting guides object tracking with high-level semantic inform…
Action assessment is a task of assessing the performance of an action. It is widely applicable to many real-world scenarios such as medical treatment and sporting events. However, existing methods for action assessment are mostly limited to individual actions, especially lacking modeling of the asym…
Most of existing object detectors usually adopt a small training batch size ( ~16), which severely hinders the whole community from exploring large-scale datasets due to the extremely long training procedure. In this paper, we propose a versatile large batch optimization framework for object detecti…
Few-shot learning, which aims at extracting new concepts rapidly from extremely few examples of novel classes, has been featured into the meta-learning paradigm recently. Yet, the key challenge of how to learn a generalizable classifier with the capability of adapting to specific tasks with severely…
Precise search of visually-similar vehicles poses a great challenge in computer vision, which needs to find exactly the same vehicle among a massive vehicles with visually similar appearances for a given query image. In this paper, we model the relationship of vehicle images as multiple grains. Foll…
Despite a lot of research efforts devoted in recent years, how to efficiently learn long-term dependencies from sequences still remains a pretty challenging task. As one of the key models for sequence learning, recurrent neural network (RNN) and its variants such as long short term memory (LSTM) and…
Most existing person re-identification (Re-ID) approaches follow a supervised learning framework, in which a large number of labelled matching pairs are required for training. This severely limits their scalability in real-world applications. To overcome this limitation, we develop a novel cross-dat…